Search

Global biodiversity loss is most pronounced in the tropics. Monitoring of broad-scale patterns of habitat is essential for biodiversity conservation. Image texture measures derived from satellite data are proxies for habitat heterogeneity, but have not been tested in tropical forests. Our goal was to evaluate image texture to predict tropical forest bird distributions across Thailand for different guilds. We calculated a suite of texture measures from cumulative productivity (1-km fPAR-MODIS data) for Thailand's forests, and assessed how well texture measures predicted distributions of 86 tropical forest bird species in relation to body size, and nesting guild. Finally, we compared the predictive performance of combining (a) satellite image texture measures, (b) habitat composition, and (c) habitat fragmentation. We found that texture measures predicted occurrences of tropical forest birds well (AUC = 0.801 ± 0.063). Second-order homogeneity was the most predictive texture measure. Our models based on texture were significantly better for birds with larger body size (p < 0.05), but did not differ among nesting guilds (p > 0.05). Models that combined texture with habitat composition measures (AUC = 0.928 ± 0.038) outperformed models that combined fragmentation with habitat composition measures (AUC = 0.905 ± 0.047) (p < 0.05). The incorporation of texture, composition, and fragmentation variables significantly improved model accuracy over texture-only models (AUC = 0.801 ± 0.063 to AUC = 0.938 ± 0.034; p < 0.05). We suggest that texture measures are a valuable tool to predict bird distributions at broad scales in tropical forests. • Satellite image texture can be a proxy for habitat heterogeneity. • We found that image texture predicted tropic bird distributions well. • Second-order homogeneity had the highest predictive power. • Texture predicted large birds especially well. • Predicting species distributions with image texture can support conservation. [ABSTRACT FROM AUTHOR]

Timely and accurate detection of crop water stress is vital for precision irrigation. Whether the accuracy of the prevailing diagnosis of crop water stress using vegetation indices (VIs) and spectral reflectance can be improved still remains to be investigated. The crop surface characteristics such as grayscale or color vary under different water stress, so in this study one more variable, image texture, was utilized together to diagnose water stress. For this end, the canopy image of winter wheat in bloom was obtained by unmanned aerial vehicle (UAV) equipped with multispectral sensor, and the effect of soil background was eliminated using vegetation index threshold method. On this basis, Grey level co-occurrence matrix (GLCM) was used to calculate the mean (MEA), variance (VAR), homogeneity (HOM), contrast (CON), dissimilarity (DIS), entropy (ENT), second moment (SEC) and correlation (COR) of the image texture under different spatial resolutions (0.008 m, 0.01 m, 0.02 m, 0.05 m, 0.1 m and 0.2 m). Next, the canopy vegetation indices were obtained by mathematical transformation of canopy reflectance, and then sensitive image texture and vegetation indices by full subset regression method. Finally, Cubist, BPNN (Back Propagation Neural Network) and ELM (Extreme Learning Machine) methods were adopted to build the estimation models of the stomatal conductance (Gs) of winter wheat (between the sensitive image texture and Gs, and between vegetation index and Gs), and the water stress map was plotted based on the optimal Gs estimation model. The result showed: (i) the image texture obtained from the high-resolution multispectral image had a high correlation with Gs, and the image texture (VAR, HOM, CON, DIS, ENT and SEC) at 550 nm had the most significant correlation; (ii) the higher the ground resolution, the higher the correlation between the Gs and the image texture, the vegetation indices, respectively. The image texture with a ground resolution of 0.008 m combined with VIs and Gs had the highest correlation, and combining image texture and vegetation index can significantly improve the estimation accuracy of winter wheat Gs; (iii) Among the three estimation models, the BPNN model constructed by combining the image texture and VIs (MEA, VAR, ENT, DWSI and EXG) had the best estimation performance (Calibration: R c 2 = 0.899, RMSE c = 0.01, MAE c = 0.006; Validation: R c 2 = 0.834, RMSE v =;0.018, MAE v = 0.014), and an accurate estimation could even be achieved at a lower Gs value. Compared with the BPNN model solely based on VIs or image texture, the R c 2 of the BPNN model based on the combined variables increased by 24% and 22.48%, respectively. Therefore, combining UAV multispectral image texture and VIs to estimate Gs provides a feasible and accurate method for water stress diagnosis of winter wheat. • The incorporation of texture improved the accuracy of water stress diagnoses with VIs. • BPNN model with VIs and texture provided the highest accuracy of Gs estimation. • UAV provides a feasible and accurate method for water stress diagnosis of winter wheat. • Removing soil background and screening methods improve the quality of remote sensing data. [ABSTRACT FROM AUTHOR]

• Propose a computer vision method for detecting asphalt pavement segregation. • Employ image texture analysis for characterizing pavement surface condition. • Extreme gradient boosting machine and deep neural network are used for classification. • Attractive repulsive center-symmetric local binary pattern is used for texture computation. • XGBoost has achieved the best detection accuracy with accuracy rate = 0.95. Aggregate segregation is a major form of defect that accelerates the pavement deterioration rate. Therefore, asphalt pavement segregation needs to be detected accurately and early during the quality survey process. This study proposes and verifies a computer vision based method for automatic identification of aggregate segregation. The new method includes Extreme Gradient Boosting Machine integrated with Attractive Repulsive Center-Symmetric Local Binary Pattern (ARCSLBP-XGBoost) and Deep Convolutional Neural Network (DCNN). Experimental results obtained from a repetitive random data sampling process with 20 runs show that the ARCSLBP-XGBoost is a capable approach for detecting asphalt pavement segregation with outstanding performance measurement metrics (classification accuracy rate = 0.95, precision = 0.93, recall = 0.98, and F1 score = 0.95). [ABSTRACT FROM AUTHOR]

This paper presents an image watermarking technique for authentication and self-recovery called AuSR2. The AuSR2 scheme partitions the cover image into 3 × 3 non-overlapping blocks. The watermark data is embedded into two Least Significant Bit (LSB), consisting of two authentication bits and 16 recovery bits for each block. The texture of each block is preserved in the recovery data. Thus, each tampered pixel can be recovered independently instead of using the average block. The recovery process may introduce the tamper coincidence problem, which can be solved using image inpainting. The AuSR2 implements the LSB shifting algorithm to increase the imperceptibility by 2.8%. The experimental results confirm that the AuSR2 can accurately detect the tampering area up to 100%. The AuSR2 can recover the tampered image with a PSNR value of 38.11 dB under a 10% tampering rate. The comparative analysis proves the superiority of the AuSR2 compared to the existing schemes. [ABSTRACT FROM AUTHOR]

• The addition of texture features could improve the accuracy of soil interpretations with remote sensing. • The optimal single-scale window size of the feature parameters was extracted. • The optimal multiscale combination of window sizes for each parameter were determined. • The multiscale fusion of texture feature windows was better than the single-scale window in soil mapping. Studying the spatial distribution of soil types is an important academic and practical issue in agriculture. With the rapid development of remote sensing technology, the role of image texture as an auxiliary variable in remote sensing identification of objects has increased. It is of great importance to ascertain the optimal window size for extracting texture features and the multiscale fusion of texture feature parameters under the optimal window for different soil types. To reach this goal, soil types in a typical area of the Jiaodong Peninsula were selected as the subject investigated, homogeneity and entropy were selected as the two texture feature parameters, and the ability to identify the different soil types based on the textural features was systematically analyzed by using Landsat 8 remote sensing images. Moreover, the optimal window sizes for extracting texture features were determined, and the role of multiscale textural features in the classification of the soil types was also evaluated. The results show that the accuracy of classification significantly increased with the addition of textural features. The optimal single-scale window sizes for the homogeneity and entropy feature parameters were 19 × 19 and 21 × 21, respectively. The fusion of multiscale textural features further improved the classification accuracy. The optimal multiscale window sizes for the homogeneity were 7 × 7, 13 × 13, 19 × 19 and 21 × 21 and those for entropy were 5 × 5, 15 × 15, 21 × 21 and 23 × 23. Therefore, the method of using texture information in remote sensing images as auxiliary variables in digital soil mapping was feasible. The method of multiscale fusion of texture features, which resulted in greater classification accuracy, was better than that of single-scale window. These conclusions could play an important guiding role in soil digital mapping with remote sensing. [ABSTRACT FROM AUTHOR]

Fault detection and diagnosis of its severity for machine health monitoring can be stated as a nested classification problem. For a faulty bearing, each fault location whether belonging to inner race, outer race or the ball can be seen as multiclass classification with three classes while the varying degree of severity in each class can be viewed as a sub classification task. The peculiar vibration patterns generated from the flaws in different bearing parts and with varying degree of distortion can be classified into various classes and subclasses for analysis of vibration signatures. This paper proposes a multiclass support vector machines (MSVMs) based fault classification approach for fault diagnosis of ball bearings. The one dimensional vibration signals are converted to two dimensional gray scale images resulting in textural patterns which are then enhanced using the wave atom transform. Features such as semivariance, skewness and entropy are extracted from the texture images and the MSVM is then trained using feature matrices generated from feature vectors. The MSVM is trained in two phases; in the first phase, the classifier categorizes the location of the fault and in the second phase the classifier does the diagnosis regarding the size of the fault at that particular location. Simulation results show that the proposed technique is highly robust in locating the fault and its severity. [ABSTRACT FROM AUTHOR]

Recent asteroid missions have revealed that many sub-kilometer asteroids are rubble piles. Large parts of their surfaces are covered with boulders larger than tens of centimeters. An evaluation of the abundance and size distribution of boulders provides clues to understand surface processes on boulder-covered asteroids. Here we report a new method that automatically measures the abundance of small boulders (sub-pixel to a few pixels), whose boundaries cannot be recognized with visual inspection, by quantifying the surface radiance variation that occurs during the spinning of the asteroid. After validating our approach with previous boulder counting data, we apply this method to images of the asteroids Ryugu and Itokawa, which were visited by JAXA's Hayabusa and Hayabusa2, and obtain a global distribution of the boulders larger than 0.75–3 ​m, which corresponds to 1.5–6 pixels. We find that the boulder number density of this size range is smaller (1) on the western bulge than on the eastern hemisphere and (2) on the equatorial ridge than on the higher latitudes, both of which exceed the number density of boulders ​> ​5 ​m by an order of magnitude. The boulder size distribution at 1.25–20 ​m shows that the boulders smaller than 1 ​m are more abundant at the equator than at mid-latitudes, while those larger than 1 ​m in diameter are more abundant at mid-latitudes than at the equator. This contrast suggests size-dependent migration of boulders in the latitudinal direction. We also find that the typical boulder size (the size reaching the cumulative areal coverage of 50%) is 1.9 ​m at the equatorial region (10°S-10°N) while it is 2.6 ​m at mid-latitudes (40°S-50°S, 40°N-50°N). The typical boulder size is also smaller in the western bulge (2.0–2.2 ​m). We construct global maps of the power-law index of the size frequency distribution of boulders and find minor variations over the entire surface of Ryugu (−2.53 ​± ​0.03) for boulders larger than 1.25 ​m. This small variation suggests homogeneous size sorting processes on Ryugu. Surface roughness does not show a significant correlation with the v-band albedo but shows a high anti-correlation (R ​= ​−0.73) with the current geological slope on the eastern hemisphere. Our method is useful enhancement of smooth area detection and boulder distribution characterization that will be applicable to other planetary explorations in the future, including those of Phobos and other asteroids. • Automatic analysis of pixel-scale boulders based on pixel radiance variation as asteroid spins. • Distribution of sub-meter boulders on Ryugu indistinguishable from visual counting. • Method detects the east-west dichotomy in the distribution of small boulders (several meters in diameter). • Uniform power-law index of boulder size frequency distribution on Ryugu suggests homogeneous size sorting. • Boulder distribution is correlated with current geologic slope. [ABSTRACT FROM AUTHOR]

Existing texture filtering techniques acquiesce in the removal of all undesired background texture patterns simultaneously, and lead to the disappearance of small-scale foreground structures. Differently, this paper considers both multi-scale structures and specified texture patterns within an image as significant image contents, and presents a content-aware texture filtering approach via an easy-to-use interactive interface, named intuitive single click. The user's effort on content-aware texture filtering is reduced to only locating a single click, where it is intuitively considered as one type of texture patterns. This simple interface is made possible by first generating three-scale intermediate filtered images (i.e., high, medium and low) and then performing breadth-first search (BFS) to identify one or more texture regions. Specifically, we utilize BFS to purify image edges in the medium-scale filtered image, on top of which a mask representing texture and non-texture regions is abstracted through the intuitive single-click texture locating and BFS. The mask is applied to effectively maintain multi-scale structures in the low-scale filtered image, and guides to fully smooth textures in the high-scale filtered image. Finally, a clean image is yielded by simply synthesizing the results of two mask operations in the low- and high-scale filtered images. We illustrate by extensive experiments that our approach advances the state-of-the-arts in terms of both the image cleanness and content-preserving ability. Our code is publicly available. • We propose a multi-scale texture filtering approach for fully removing textures while preserving image contents effectively. • We propose a texture-aware approach for segmenting an image into contents and texture regions. • We provide an easy-to-use interactive system for allowing users to removing different types of texture patterns. [ABSTRACT FROM AUTHOR]

• Cities are dominated by private lands which presents a challenge for field study. • LiDAR data characterizes indices of avifaunal habitat on private residential lands. • NDVI, image texture, and land cover data are weaker predictors of urban avifauna. • LiDAR combined with street tree data has the strongest predictive power for urban birds. • High-resolution remote sensing data should be utilized in urban avifaunal studies. Urban ecosystems are dominated by private lands which poses a significant hurdle to performing field-based assessment of wildlife. An alternative approach is to characterize indices of animal habitat in difficult-to-access areas using data from airborne remote sensing platforms. Characterizing indices of wildlife habitat using remotely sensed data is common in natural systems but has received less attention within urban ecosystems. We tested the utility of using remotely sensed data from high-resolution airborne sensors, including LiDAR, a measure of vertical habitat structure, NDVI, a measure of greenness, image texture, a measure of horizontal habitat structure, and parcel level land-cover data, along with field-based street-tree measurements to predict bird abundance and richness across Greater Los Angeles, California, USA. We surveyed birds and gathered street-tree data on public lands of residential neighborhoods and processed the remote sensing data in 50-m and 300-m circular buffers of bird survey locations to capture data primarily on private, residential land across three winter field seasons (2016–18, 2019/20) at 23 locations along a tree-canopy cover gradient. Data from LiDAR processed as an index for the density of trees summarized in the 50-m and 300-m extents were the strongest univariate predictors of avifaunal abundance and richness explaining 75 % and 74 % of the likelihood in fitted models. NDVI, image texture, land cover, and street-tree density measures were weaker univariate predictors than models fitted with LiDAR data. Models including LiDAR and ground-based street-tree measurements accounted for upwards of 80 % of the variability in avifaunal abundance and richness, particularly for bird species associated with trees and shrubs. We recommend the prioritization of high-resolution remote sensing data, particularly LiDAR, in combination with field-based habitat measures e.g., street trees, to characterize indices of avifaunal habitat on public and private lands of cities, which could help to improve our understanding of the distribution of birds across urban areas. [ABSTRACT FROM AUTHOR]

Due to the emphasis on sustainable development and environmental protection, searching for new technologies in the production of fruit and vegetables is essential. Organic farming using natural preparations is aimed to produce healthy food, rich in nutrients that is unmodified and uncontaminated. Pepper fruit is characterized by its valuable chemical composition and dietary and taste values. The available information on the influence of natural preparations on pepper fruit is insufficient. Therefore, this study was aimed at evaluating the influence of the natural preparations and plant extracts, such as organic fertilizer - Bio-algeen S90, growth and development stimulator - Natural Crop® SL, nettle extract (fertilizer with a killing and nutritional effect) on the chemical composition, structure (image texture), and sensory quality of Devito F 1 and Sprinter F 1 pepper fruit in organic greenhouse cultivation under the conditions for organic farming. The combination of measurements of chemical properties, flesh image features, and sensory analysis for assessing the quality of pepper treated with these preparations is a great novelty of this study. The obtained results showed that the use of Bio-algeen S90 and Natural Crop® SL had an impact on the increase in the total yield compared to the control samples. Furthermore, the application of Bio-algeen S90 and Natural Crop® SL increased the content of nutrients and health-promoting compounds, such as total sugars, l -ascorbic acid, total polyphenols, and carotenoids for both pepper cultivars Devito F 1 and Sprinter F 1. The applied natural preparations had an impact on the flesh structure, which was greater for pepper Devito F 1. The selected image textures allowed for distinguishing pepper slices in terms of natural preparations with higher accuracies for Devito F 1 than Sprinter F 1. However, in the case of both cultivars, the samples treated with NaturalCrop® SL were the most different from the control. Natural preparations were not affecting significantly the sensory attributes of pepper fruit. All treated samples were characterized by high sensory quality. • The influence of the Bio-algeen S90, Natural Crop® SL, and nettle extract on pepper was examined. • The chemical properties, image parameters, and sensory attributes were determined. • The highest effect of NaturalCrop® SL on pepper fruit was confirmed. [ABSTRACT FROM AUTHOR]

Objectives: To compare deep learning (True Fidelity, TF) and partial model based Iterative Reconstruction (ASiR-V) algorithm for image texture, low contrast lesion detectability and potential dose reduction.Methods: Anthropomorphic phantoms (mimicking non-overweight and overweight patient), containing lesions of 6 mm in diameter with 20HU contrast, were scanned at five different dose levels (2,6,10,15,20 mGy) on a CT system, using clinical routine protocols for liver lesion detection. Images were reconstructed using ASiR-V 0% (surrogate for FBP), 60 % and TF at low, medium and high strength. Noise texture was characterized by computing a normalized Noise Power Spectrum filtered by an eye filter. The similarity against FBP texture was evaluated using peak frequency difference (PFD) and root mean square deviation (RMSD). Low contrast detectability was assessed using a channelized Hotelling observer and the area under the ROC curve (AUC) was used as figure of merit. Potential dose reduction was calculated to obtain the same AUC for TF and ASiR-V.Results: FBP-like noise texture was more preserved with TF (PFD from -0.043mm-1 to -0.09mm-1, RMSD from 0.12mm-1 to 0.21mm-1) than with ASiR-V (PFD equal to 0.12 mm-1, RMSD equal to 0.53mm-1), resulting in a sharper image. AUC was always higher with TF than ASIR-V. In average, TF compared to ASiR-V, enabled a radiation dose reduction potential of 7%, 25 % and 33 % for low, medium and high strength respectively.Conclusion: Compared to ASIR-V, TF at high strength does not impact noise texture and maintains low contrast liver lesions detectability at significant lower dose. [ABSTRACT FROM AUTHOR]

The quantitative measure of irregular arrangement, configuration and geometric pattern of microstructural features is often termed as fractal dimension (D f). The measurement of D f of a complex mixture of multiphase microstructure, comprised of crystals consisting of martensite, bainite, Fe 3 C and martensite/austenite (M/A) constituents' chaos networks in a typical dual phase steel (matrix ferrite) is carried out and interpreted with its respective phase fractions and resulting mechanical responses as a function of intercritical annealing schedule. Image–texture characteristics have also been analyzed to comprehend the s t o r e d – e n e r g y and c o n f i g u r a t i o n a l – s t a b i l i t y of such complex phase-mixture with annealing temperature. The invasive-type fractal characteristics, complexities and chaos of such micro layered hierarchical multiphases' networks in the multiphase steel has been convincingly revealed. • Multiphase DP steel is chosen at different intercritical annealed states. • Box-counting method is employed to estimate fractal dimension of second phase mixture. • Image–texture analysis is performed to understand the relative 'energy generation' of multiphases. • Fractality-image texture-microhardness correlated at different microstructural states. [Display omitted] [ABSTRACT FROM AUTHOR]

This study innovatively applies digital imaging techniques to quantify the irregular nanoscale roughness of the surfaces of plasma-etched, hydrophobic polymer films. The main objective is to verify meaningful roughness indicators that predict the surface wettability by quantifying the surface nanostructures in a simple way. Five texture parameters were extracted from SEM images by box-counting and a gray-level co-occurrence matrix (GLCM) algorithm, which together provide 2D spatial information of roughness features. Also, five parameters related to height and aspect ratio profiles of roughness were obtained using AFM analysis. The 2D texture parameters and AFM roughness profiles were statistically correlated, and either set could be used to predict surface wettability with high explanatory power. The prediction was most powerful when variables of fractal dimension , arithmetic mean height Ra of roughness features in the assessed area, and skewness Rsk of height in the assessed area were used in the regression model. This result indicates that both the height profile and 2D spatial distribution of roughness features strongly affect surface wettability. The correlation of gray levels with the neighboring pixels was statistically correlated with Ra and Rsk , and a simple predictive model was developed using fractal dimension and correlation. This research is significant in that it explored a novel analytical approach in assessing the roughness characteristics to predict surface wettability. Ultimately, we anticipate that the developed approach can be applied in designing relevant process parameters to control the wetting properties. • This study explores use of digital imaging techniques to predict surface wettability of plasma-etched, hydrophobic films. • Image texture parameters could be used as alternatives to AFM roughness parameters to quantify irregular nano-roughness. • Image texture parameters could be used to predict surface wettability with high explanatory power. • Both the height profile and 2D spatial distribution of roughness features strongly affect surface wettability. [ABSTRACT FROM AUTHOR]

A few well-annotated datasets for land-cover semantic segmentation have recently been introduced to advance the field of earth observation technologies. However, these datasets overlook the significant diversity among geographic areas with different climates, which can greatly impact and diversify land cover. Consequently, this leads to a domain gap in remote sensing images and severe performance degradation of the segmentation models. To enhance land-cover semantic segmentation with improved generalization ability, we conducted the first investigation into the impact of climate on this task. In this paper, we present a unique large-scale Climate-Aware Satellite Images Dataset (CASID) specifically designed for domain adaptive land-cover semantic segmentation. It consists of 980 satellite images with a size of 5000 × 5000 pixels, collected from 30 different regions around Asia, covering over 24,500 square kilometers. These images are gathered from four distinct climate zones, namely temperate monsoon, subtropical monsoon, tropical monsoon, and tropical rainforest. It includes four sub-datasets/domains, each representing one of the aforementioned climate zones. This characteristic makes CASID the first climate-aware land-cover semantic segmentation dataset with multiple domains. Additionally, we provide a comprehensive analysis of the samples from the four climate zones, emphasizing differences in global image features, image texture, category distribution, spectral value, and object shape. These analyses offer valuable insights for subsequent research in this field. Moreover, we conduct extensive experiments to evaluate the latest semantic segmentation and unsupervised domain adaptation methods on the CASID dataset. These results serve as a robust baseline for future research endeavors. Our dataset will be made publicly available soon at the following link: https://github.com/Linwei-Chen/CASID. [ABSTRACT FROM AUTHOR]

• An almost complete review of current methods for feature extraction from underwater acoustic signals. • Developing a reliable and accurate model for distinguishing Underwater vessel-radiated acoustical noise (UVRAN), which is robustness to noise. • Converting complex marine signals to images using the Gramian angular field (GAF) technique and extracting second-order image statistics by image texture analysis for the first time. • extracting more discriminative information from the UVRAN by signal-to-image transformation. • Designing a parameter called spectral amplitude mean difference function (SAMDF) that is more suitable for encoding to an image than the original signal. Underwater vessel-radiated acoustical noise (UVRAN) is a major factor for classification in the sea by the SONAR. Due to unsteady and complex maritime ambient, analyzing underwater sound signals is a challenging issue that has lately received attention in the marine field. In the conventional feature extraction methods, to reduce the effect of ocean noise, the de-noising procedure is performed before complexity measurement by mode decomposition techniques. Based on this, we propose a novel insight for the first time to distinguish the objects which made the underwater noises as the hydro-acoustic signature, using a signals-to-image conversion without noise removal. After pre-processing, the spectral amplitude mean difference function is encoded into an image using Gramian angular field (GAF) technique. Subsequently, image texture analysis is performed in which GAF images are subjected to the gray-level co-occurrence matrix (GLCM). Finally, the second-order image statistic (i.e., 2-D permutation entropy) is calculated. Compared with other methods, results demonstrate that the proposed method has a high degree of separation and stability between the various kinds of underwater targets, suggesting that the methodology is superior to the existing methods. Moreover, our model is robust to noise. The approach perhaps opens an alternative path for UVRAN discrimination. [ABSTRACT FROM AUTHOR]

Crop lodging detrimentally affects crop yield and mechanical harvest efficiency. Traditional remote sensing-based methods primarily focus on the identification and area extraction of lodging using image texture and spectrum. However, the response of image texture and spectrum to lodging is indirect and varies under diverse conditions. Moreover, other important finer details of lodging phenotyping, such as lodging angle and lodging type, have frequently been neglected. In this study, a robust and accurate method was developed for investigating lodging phenotypes in the field. The method was based on the three-dimensional morphological information of rapeseed (Brassica napus L.) canopy reconstructed from unmanned aerial vehicle (UAV) images. In contrast to traditional remote sensing methods that only identify lodging targets and their respective areas, the novel method in this study calculated the total lodging angle (TLA), root lodging angle (RLA), stem lodging angle (SLA = TLA - RLA), and lodging types according to a morphological method and a lodging classification model. Initially, the method employed a geometric model to characterize the stalk shape of lodged rapeseed. After assessing numerous lodging samples from individual rapeseed plants, the circle function was identified as the optimal geometric model. With this optimal function, the canopy height derived from the UAV images was found effective in calculating TLA, RLA, and SLA across 24 rapeseed cultivars in five climatic zones within the Yangtze River Basin (YRB) in China. Results showed that the average root mean square error (RMSE) was 8.3° for TLA and 7.4° for RLA. Subsequently, based on field measured data of SLA and RLA, a decision tree model was constructed to classify lodging types and an accuracy of 95.4% was achieved. Using the classification model and estimated values of RLA and SLA, the spatial distribution information and specific area estimates for different lodging types were obtained. Based on the analysis of these results, the rapeseed cultivars Zhongshuang 11 and Dadi 199 were determined to be the dominant cultivars with lodging resistance in the YRB, even though they did not achieve the mean high yields in multiple climatic zones. However, the lodging-prone cultivars such as Qinyou7 and Qinyou33 fell under the low-yield level in all climatic zones. The robust and cost-effective method proposed in this study for acquiring detailed crop lodging phenotyping data has the potential to enhance mechanized harvesting, accurately estimate the risk of low yield, and assess the lodging status of various crops. • Circle functions can simulate most stalk shapes of lodged rapeseed. • Two phases of UAV images are found effective to estimate total lodging angle. • Root and stem lodging angle can be estimated using circle functions and UAV images. • Lodging types can be distinguished by root lodging angle and stem lodging angle. [ABSTRACT FROM AUTHOR]

Superficial fibromatosis exhibits variable MR signal intensity due to collagenous and fibroproliferative components. Quantifying this signal heterogeneity using image texture analysis and T2-mapping could have prognostic and therapeutic implications. This IRB-approved retrospective study included 13 patients with superficial fibromatosis, managed by observation, electron beam radiotherapy (EBT), or pentoxifylline/vitamin E. Two-dimensional regions of interest (ROIs) were drawn on proton-density or T2-weighted MRI for radiomics feature analysis, and corresponding T2-maps. Comparisons were made between baseline and follow-up T2 relaxation times and radiomics features: Shannon's entropy, kurtosis, skewness, mean of positive pixels (MPP), and uniformity of distribution of positive gray-level pixel values (UPP). There were 19 nodules in 13 subjects. Mean patient age was 60 years; 62% (8/13) were female; mean follow-up was 9.7 months. Nodule diameter at baseline averaged 18.2 mm (std dev 16.2 mm) and decreased almost 10% to 16.6 mm (p = 0.1, paired t -test). Normalized T2 signal intensity decreased 23% from 0.71 to 0.55 (p = 0.03, paired t -test). T2 relaxation time decreased 16% from 46.5 to 39.1 ms (p < 0.001, paired t -test). Among radiomics features, skewness increased to 0.71 from 0.41 (p = 0.03, paired t -test), and entropy decreased from 8.37 to 8.03 (p = 0.05, paired t-test); differences in other radiomics features were not significant. Radiomics analysis and T2-mapping of superficial fibromatosis is feasible; robust decreases in absolute T2 relaxation time, and changes in image textural features (increased skewness and decreased entropy) offer novel imaging biomarkers of nodule collagenization and maturation. • T2 mapping, image texture analysis show longitudinal changes in superficial fibromatoses. • Treated nodules show decreased T2 relaxation times, reflecting increased collagenization. • Increased skewness and decreased entropy indicate homogeneity accompanies response. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have performed well in image denoising. Although some CNNs enlarge convolutional kernels and increase stacked convolutional layers to overcome the locality defect of convolutional operations, they may increase computational costs. In this paper, we propose a parallel and serial denoising network (PSDNet) for image denoising to preserve image texture. Specifically, the proposed PSDNet contains a parallel block (PB), a serial block (SB), and a reconstruction block (RB). A PB uses two heterogeneous sub-networks with a deformable convolution in a parallel way to extract comparative information for better-recovering image texture. A SB utilizes an enhanced residual dense architecture via combinations of a batch normalization, ReLU, and convolutional layer in a serial way to refine obtained features for obtaining more accurate noise information. A RB is responsible for reconstructing images. Experimental results reveal that our PSDNet is very effective in image denoising, according to quantitative analysis and visual analysis. Codes can be obtained at https://github.com/hellloxiaotian/PSDNet. • Heterogeneous architecture with deformable convolution can better filter noise. • An enhanced residual architecture is used to remove redundant features. • Combining a parallel and serial way can improve effects of images denoising. • Proposed network is effective for synthesized and real noisy image denoising. [ABSTRACT FROM AUTHOR]

Precise information on tree species composition is critical for forest management and conservation, but mapping tree species with satellite data over large areas is still a challenge. Since 2017, Sentinel-2A/B provide multi-spectral time series with global coverage at an unprecedented spatial and temporal resolution. This is a new opportunity for mapping tree species over large areas that has not yet been fully explored. Because of the high spatial and temporal resolution, Sentinel-2 time series improve the characterization of vegetation phenology and canopy structure, parameters that are intrinsically linked to tree species. The objective of this study was to test the utility of a Sentinel-2 time-series based approach for mapping tree species in a temperate forest region in Central Europe. Using stand-wise forest inventory data for single species stands we assess how well main and minor tree species can be mapped, and if the addition of environmental variables and spatial texture metrics improves the classification accuracy. Our time series approach utilizes all available Sentinel-2 observations and an ensemble of radial basis convolution filters to build cloud-free 5-day time series for each spectral band. The time series are then used as input features to classify seventeen tree species. Our results show the potential of Sentinel-2 time-series based classification, but they also show the challenges associated with mapping a diverse portfolio of tree species. Accuracy of the nine main species, with an area proportion greater than 0.5%, ranged between 98.9% and 66.8%, which is promising for a large area. Adding detailed environmental data and texture metrics to the spectral model only marginally increased the accuracy of a few minor tree species. Overall, the eight minor tree species with area proportions less than 0.5% were most strongly affected by classification errors. Although the absolute mapped area of minor species correlated well with the estimated reference area, the small class areas of minor species lead to high classification errors in relative terms. Mapping minor tree species is challenging for statistical reasons (i.e., class imbalance, small sample size and class variance). Using all available Sentinel-2 data allows building dense time series at high spatial resolution that are mandatory for improved tree species mapping. We were able to show that the spectral time series is the prime explanatory information, even when complementing our analyses with texture information and various environmental data. The results suggest that with the applied data harmonization approach precise regional tree species mapping is feasible. • Sentinel-2A/B time series used for mapping of 17 tree species on regional scale. • Adaptive ensemble filter produced cloud-free 5-day time series over varying data density. • Major species with area shares >0.5% were mapped with medium to high accuracy. • Maps reflect area proportions of minor tree species but with low spatial accuracy. • Environmental variables and texture metrics did not substantially improve accuracy. [ABSTRACT FROM AUTHOR]

• Ultrahigh-resolution PCD-CT produces images with inherently higher noise level. • QIR reduces noise without affecting image texture. • QIR does not compromise sharpness or stenosis measurements on coronary CTA series. • The most benefit is observed at the highest QIR strength level. To assess the impact of different quantum iterative reconstruction (QIR) levels on objective and subjective image quality of ultra-high resolution (UHR) coronary CT angiography (CCTA) images and to determine the effect of strength levels on stenosis quantification using photon-counting detector (PCD)-CT. A dynamic vessel phantom containing two calcified lesions (25 % and 50 % stenosis) was scanned at heart rates of 60, 80 and 100 beats per minute with a PCD-CT system. In vivo CCTA examinations were performed in 102 patients. All scans were acquired in UHR mode (slice thickness0.2 mm) and reconstructed with four different QIR levels (1–4) using a sharp vascular kernel (Bv64). Image noise, signal-to-noise ratio (SNR), sharpness, and percent diameter stenosis (PDS) were quantified in the phantom, while noise, SNR, contrast-to-noise ratio (CNR), sharpness, and subjective quality metrics (noise, sharpness, overall image quality) were assessed in patient scans. Increasing QIR levels resulted in significantly lower objective image noise (in vitro and in vivo: both p < 0.001), higher SNR (both p < 0.001) and CNR (both p < 0.001). Sharpness and PDS values did not differ significantly among QIRs (all pairwise p > 0.008). Subjective noise of in vivo images significantly decreased with increasing QIR levels, resulting in significantly higher image quality scores at increasing QIR levels (all pairwise p < 0.001). Qualitative sharpness, on the other hand, did not differ across different levels of QIR (p = 0.15). The QIR algorithm may enhance the image quality of CCTA datasets without compromising image sharpness or accurate stenosis measurements, with the most prominent benefits at the highest strength level. [ABSTRACT FROM AUTHOR]

Scattering and attenuation of light in no-homogeneous imaging media or inconsistent light intensity will cause insufficient contrast and color distortion in the collected images, which limits the developments such as vision-driven smart urban, autonomous vehicles, and intelligent robots. In this paper, we propose an all-in-one scene recovery network via multi-knowledge integration (termed AoSRNet) to improve the visibility of imaging devices in typical low-visibility imaging scenes (e.g., haze, sand dust, underwater, and low light). It combines gamma correction (GC) and optimized linear stretching (OLS) to create the detail enhancement module (DEM) and color restoration module (CRM). Additionally, we suggest a multi-receptive field extraction module (MEM) to attenuate the loss of image texture details caused by GC nonlinear and OLS linear transformations. Finally, we refine the coarse features generated by DEM, CRM, and MEM through Encoder-Decoder to generate the final restored image. Comprehensive experimental results demonstrate the effectiveness and stability of AoSRNet compared to other state-of-the-art methods. The source code is available at https://github.com/LouisYuxuLu/AoSRNet. • AoSRNet can enhance imaging quality in hazy, sandy, underwater, and low-light scenes. • Multi-knowledge integration can robustly restores image in unpredictable scenes. • Optimized linear stretching and gamma correction improve AoSRNet's generalization. • We constructed a set of atmospheric light values for haze and sand image synthesis. • Extensive experiments verify AoSRNet's effectiveness with start-of-the-art methods. [ABSTRACT FROM AUTHOR]

• The Contrast Texture Feature Values (CTFV) is proposed to extract subtle changes in the thermal image caused by crack evolution based on the Gray Level Co-occurrence Matrix (GLCM). • The cumulative Crack Texture Thermal Image (CTTI) is reconstructed using CTFV, which can reflect the spatial evolution process of loading coal and rock cracks. • The CTFV can provide readily identifiable precursor information for the coal and rock failure, and the precursor can be divided into high risk, medium risk, and low risk levels based on different gray levels. • An anomaly detection method for CTFV was proposed based on sliding window probability density estimation to achieve real-time and adaptive recognition of rock failure precursors. Early warning of the catastrophic failure of rocks is a challenging rock mechanics problem. This article proposed a failure precursor recognition method based on infrared thermal image texture features for coal and rock. Based on spatiotemporal background noise correction for infrared thermal images, a new thermal image parameter of loading coal and rock, Contrast Texture Feature Values (CTFV), is proposed to extract subtle changes in the thermal image caused by crack evolution based on the Gray Level Co-occurrence Matrix (GLCM). The cumulative Crack Texture Thermal Image (CTTI) is reconstructed using CTFV, which can accurately reflect the spatial evolution process of loading coal and rock cracks. The CTFV remains at 0 in the early stage of loading and gradually increases with stress increase at the unstable crack propagation stage, which can serve as a reference for precursor warning of coal and rock failure. For shale, sandstone, and limestone, the precursor of CTFV at grayscale levels of 7, 8, and 9, can be classified into high failure risk, medium failure risk, and low failure risk, respectively. For coal samples, the CTFV is only applicable for the critical warning of high failure risk when the grayscale level is 7. Then, an adaptive identification method for failure precursors based on the sliding window probability density estimation method is proposed. The research results can enhance the reliability of IR monitoring technology for rock failure and instability early warning and can provide support for the prevention and control of rock engineering and geological disasters. [ABSTRACT FROM AUTHOR]

This article focuses on the characterization and analysis of dimple geometry on the published tensile fracture surfaces of a HfNbTaTiZr refractory high entropy alloy of different matrix microstructures, generated through cold deformation and systematic annealing treatments. Changes in different microstructural states which led to different tessellated fracture complexions have been quantified, compared and correlated with the corresponding tensile responses of the alloy. This interpretation allows the use of fracture surface morphology and image texture in a quantitative way. • A HfNbTaTiZr high entropy alloy is chosen for fracture feature analysis at six different initial microstructural states. • Two-dimensional dimple geometry is measured on tensile fractographs. • Quantitative fractography is employed to measure dimple geometry. • Image texture analysis on fractographs is performed to understand relative 'energy generation' during ductile fracture. • Dimple geometry-image texture-mechanical property correlated with microstructural states. [ABSTRACT FROM AUTHOR]

Fractal dimension of a microstructural feature is a measure of its geometric complexity, morphological characteristics and irregularities in configurations. The experimental measurements of fractal dimensions of a novel-flaky microstructure, comprising the crystals with hierarchical 3D nanolayered α/β-Zr networks in Zr-2.5Nb alloy have been performed and correlated with its corresponding mechanical properties as a function of annealing temperature. Image texture analysis has also been performed to understand the stored-energy and thermal stability of these α/β-Zr networks. The invasive fractal-character and chaos of these networks have been convincingly revealed. [Display omitted] [ABSTRACT FROM AUTHOR]

• Comparison of PE2D with the novel AAPE2D entropy algorithm. • Texture analysis of synthetic and biomedical images. • Both methods statistically differentiate healthy and pneumonia subjects. • AAPE2D features achieve 75.5% accuracy, which is slightly better than PE2D. Entropy algorithms have been applied extensively for time series analysis. The entropy value given by the algorithm quantifies the irregularity of the data structure. For higher irregular data structures, the entropy is higher. Both permutation entropy (PE) and amplitude-aware permutation entropy (AAPE) have been previously used to analyze time series. These two metrics have the advantage, over others, of being computationally fast and simple. However, fewer entropy measures have been proposed to process images. Two-dimensional entropy algorithms can be used to study texture and analyze the irregular structure of images. Herein, we propose the extension of AAPE for two-dimensional analysis (AAPE 2 D). To the best of our knowledge, AAPE 2 D has never been proposed to analyze texture of images. For comparison purposes, we also study the two-dimensional permutation entropy (PE 2 D) to analyze the effect of the amplitude consideration in texture analysis. In this study, we compare AAPE 2 D method with PE 2 D in terms of irregularity discrimination, parameters sensitivity, and artificial texture differentiation. Both AAPE 2 D and PE 2 D appear to be interesting entropy-based approaches for image texture analysis. When applied to a biomedical dataset of chest X-rays with healthy subjects and pneumonia patients, both methods showed to statistically differentiate both groups for P < 0.01. Finally, using a SVM model and multiscale entropy values as features, AAPE 2 D achieves an average of 75.7% accuracy which is slightly better than the results of PE 2 D. Overall, both entropy algorithms are promising and achieve similar conclusions. This work is a new step towards the development of other entropy-based texture measures. [ABSTRACT FROM AUTHOR]

• A robustness analysis on quantitative ultrasound texture features was done varying the dynamic range and beamforming method. • Ultrasound image texture parameters are robust to changes in the dynamic range values considered in our study. • Texture parameters are altered when employing different beamforming methods. • Different beamformers could potentially discriminate better between healthy/pathological tissues. Texture analysis of medical images gives quantitative information about the tissue characterization for possible pathology discrimination. Ultrasound B-mode images are generated through a process called beamforming. Then, to obtain the final 8-bit image, the dynamic range value must be set. It is currently unknown how different beamforming techniques or dynamic range values may alter the final image texture. We provide here a robustness analysis of first and higher order texture features using six beamforming methods and seven dynamic range values, on experimental phantom and in vivo musculoskeletal images acquired using two different ultrasound research scanners. To investigate the repeatability of the texture parameters, we applied the multivariate analysis of variance (MANOVA) and estimated the intraclass correlation coefficient (ICC) on the texture features calculated on the B-mode images created with different beamforming methods and dynamic range values. We demonstrated the high repeatability of texture features when varying the dynamic range and showed texture features can differentiate between beamforming methods through a MANOVA analysis, hinting at the potential future clinical application of specific beamformers. [ABSTRACT FROM AUTHOR]

• ImmunoPET is a potential biomarker for patient selection to immunotherapy. • Patient response classification differs with tumor measurement strategy. • MPM tumor volumetry predicts patient survival and outperforms CT volumetry. • CT image texture has potential to differentiate among MPM tumor histologies. • Skeletal muscle loss in chemotherapy patients demonstrates prognostic potential. Imaging of mesothelioma plays a role in all aspects of patient management, including disease detection, staging, evaluation of treatment options, response assessment, pre-surgical evaluation, and surveillance. Imaging in this disease impacts a wide range of disciplines throughout the healthcare enterprise. Researchers and clinician-scientists are developing state-of-the-art techniques to extract more of the information contained within these medical images and to utilize it for more sophisticated tasks; moreover, image-acquisition technology is advancing the inherent capabilities of these images. This paper summarizes the imaging-based topics presented orally at the 2021 International Conference of the International Mesothelioma Interest Group (iMig), which was held virtually from May 7–9, 2021. These topics include an update on the mesothelioma staging system, novel molecular targets to guide therapy in mesothelioma, special considerations and potential pitfalls in imaging mesothelioma in the immunotherapy setting, tumor measurement strategies and their correlation with patient survival, tumor volume measurement in MRI and CT, CT-based texture analysis for differentiation of histologic subtype, diffusion-weighted MRI for the assessment of biphasic mesothelioma, and the prognostic significance of skeletal muscle loss with chemotherapy. [ABSTRACT FROM AUTHOR]

• Entropy of image texture reveals densification, clarification, and sorting of sludge. • Dynamic entropy effectively differentiates various types of granular sludge. • Prompt sorting during the settling process indicates stable granulation. • Image-based monitoring correlate with respirogram indexes. Aerobic granular sludge is one of the most promising biological wastewater treatment technologies, yet maintaining its stability is still a challenge for its application, and predicting the state of the granules is essential in addressing this issue. This study explored the potential of dynamic texture entropy, derived from settling images, as a predictive tool for the state of granular sludge. Three processes, traditional thickening, often overlooked clarification, and innovative particle sorting, were used to capture the complexity and diversity of granules. It was found that rapid sorting during settling indicates stable granules, which helps to identify the state of granules. Furthermore, a relationship between sorting time and granule heterogeneity was identified, helping to adjust selection pressure. Features of the dynamic texture entropy well correlated with the respirogram, i.e., R2 were 0.86 and 0.91 for the specific endogenous respiration rate (SOUR e) and the specific quasi-endogenous respiration rate (SOUR q), respectively, providing a biologically based approach for monitoring the state of granules. The classification accuracy of models using features of dynamic texture entropy as an input was greater than 0.90, significantly higher than the input of conventional features, demonstrating the significant advantage of this approach. These findings contributed to developing robust monitoring tools that facilitate the maintenance of stable granular sludge operations. [Display omitted] [ABSTRACT FROM AUTHOR]

• A novel PDE-constrained optimization problem is proposed for MRI denoising task. • The proposed optimization procedure computes the variable exponent and the clean image for MRI images. • The comparative results demonstrates the performance on two MRI datasets This paper investigates a novel PDE-constrained optimization model with discontinuous variable exponent p (x) identification. Since the parameter p is always related to a better approximation of the image gradient, its computation plays a critical role in preserving the image texture. Analytically, we include results on the approximation of this parameter as well as the resolution of the encountered PDE in a well posed framework. In addition, to resolve the PDE-constrained minimization problem, we proposed a modified primal-dual algorithm. Finally, numerical results are provided to compute the parameter p and also to remove high intensity of noise. The proposed algorithm simultaneously keep safe fine details and important features in medical image applications (Magnetic Resonance Images (MRI)) with numerous comparisons to show the performance of the proposed approach. [ABSTRACT FROM AUTHOR]

[Display omitted] • Gray-level Co-occurrence Matrix was applied to SEM image texture analysisPearson analysis of DEPs with sensory attributes and chemical composition. • 55 differentially expressed proteins (DEPs) significant correlated with sensory properties. • 69 DEPs associated with mutable collagenous tissues (MCTs) structures. The microstructure of the body wall, body wall composition, and collagen fibers of sea cucumber (Stichopus japonicus) under different heating times (1 h, 4 h, 12 h, and 24 h) was investigated based on heat treatment at 80 °C. A Label-Free proteomics technique was applied to study the proteomic changes in the body wall of sea cucumbers under 4 and 12 h of heat treatment. Compared with the fresh group, 981 proteins were found to be differentially expressed proteins (DEPs) after heat treatment at 80 °C (4 h), and 1110 DEPs were observed after heat treatment at the same temperature for 12 h. There were 69 DEPs associated with mutable collagenous tissues (MCTs) structures. The results of correlation analysis showed that 55 DEPs were correlated with sensory properties, among which A0A2G8KRV2 was significantly correlated with hardness and SEM image texture features (SEM_Energy, SEM_Correlation, SEM_Homogeneity, and SEM_Contrast). These findings could be conducive to further comprehension of the structural changes and mechanisms of quality loss in the body wall of sea cucumbers at different heat treatment times. [ABSTRACT FROM AUTHOR]

Waste generation is a continuous process that needs to be managed effectively to ensure environmental safety and public health. The recent circular economy (CE) practices have brought a new shape for the waste management industry, creating value from the generated waste. The shift to a CE represents one of the most significant challenges, particularly in sorting and classifying generated waste. Addressing these challenges would facilitate the recycling industry and helps in promoting remanufacturing. But in the COVID times, most of the generated waste is getting mixed with conventional waste types, especially in the global south. The pandemic has resulted in colossal infectious waste generation. Its handling became the most significant challenge raising fears and concerns over sorting and classifying. Hence, this study proposes an Artificial Intelligence (AI) based automated solution for sorting COVID related medical waste streams from other waste types and, at the same time, ensures data-driven decisions for recycling in the context of CE. Metal, paper, glass waste categories, including the polyethylene terephthalate (PET) waste from the pandemic, are considered. The waste type classification is done based on the image-texture-dependent features, which provided an accurate sorting and classification before the recycling process starts. The features are fused using the proposed decision-level feature fusion scheme. The classification model based on the support vector machine (SVM) classifier performs best (with 96.5 % accuracy, 95.3 % sensitivity, and 95.9 % specificity) in classifying waste types in the context of circular manufacturing and exhibiting the abilities to manage the COVID related medical waste mixed. [ABSTRACT FROM AUTHOR]

Uranium ore concentrates (UOCs) are produced in the early stages of the nuclear fuel cycle, prior to conversion to uranium hexafluoride. Because of their high uranium content and the large-scale production, UOCs diversion from civilian use and proliferation are potential risks. This implies the necessity to develop methods able to recognise characteristic parameters correlating each UOC powder to its history and origin. Here, a novel methodology is proposed: first the reflectance spectra of 79 commercial UOCs are acquired and clustered by means of Ward's clustering analysis, then classified by Support Vector Machine (SVM). Second, SVM classification is applied to the image textural features extracted with the Grey Level Co-occurrence Matrix (GLCM) and the Angle Measure Technique (AMT) algorithms for powders in two different colour groups. The developed SVM models present good classification quality: a Matthews correlation coefficient (MCC) of 0.95 is obtained for the classification based on colours while macro-F1 is generally greater than 0.81 (MCC larger than 0.75) for the texture-based classification. These results reveal the potentiality of the present automated classification for the scopes of nuclear forensics in the identification of an unknown uranium ore concentrate sample. [Display omitted] • Illicit trafficking of uranium ore concentrates is a realistic risk. • Nuclear Forensics requires reliable methods to determine uranium ore concentrates origin. • Spectrophotometry and image texture analysis are powerful techniques for powders characterisation. • Support Vector Machine enables the identification of an unknown uranium ore concentrate sample. [ABSTRACT FROM AUTHOR]

The goal of infrared and visible image fusion is to generate an informative image that preserves the complementary information of the two types of source images, such as texture details and infrared targets. Existing methods have designed a variety of means to achieve the fusion of image texture and target complementary information. But they ignore the fact that the two types of source images have the complementarity of illumination, especially the infrared image can mainly supplement the information of the low-light visible image. An image fusion method using infrared and visible light to supplement light interactively is proposed. It performs intrinsic image decomposition on the input infrared and visible light images respectively and then fuses the illumination components and material components of the two types of images respectively. Further, to better meet the needs of image fusion, an improved variational model for the decomposition of image intrinsics is proposed. Experimental results demonstrate the effectiveness of the proposed model with its algorithm. Compared with the state-of-the-art methods, the significant advantage of the proposed method is that it has better fusion accuracy and visual perception at the same time, and the comprehensive metric evaluation is the best (9.2% performance improvement). The code is available at https://github.com/skyworkds/IFICI. • An improved intrinsic image decomposition suitable for image fusion is proposed. • A image fusion method based on interactive compensation illumination is proposed. • Experiments show that our method has obvious advantages. [ABSTRACT FROM AUTHOR]

• We first noticed the importance of similar and heterogeneous pixel gradients in feature extraction. • Introducing clustering algorithms into the field of image fusion to improve feature extraction capabilities. • Using source image gradients instead of the clustering base layer of traditional algorithms. Image fusion is performed to merge the information of different source images into one image. In this study, a fusion algorithm based on the pixel mean shift and source image gradient was proposed to make the background of the fused image clear and the target prominent. First, a pixel spatial average kernel function was designed to separate the image texture and the significant target during pixel density migration. In this study, a novel approach is presented that distinguishes itself from other methods in two distinct ways. Firstly, it segregates the texture details of dissimilar pixel regions and captures the texture characteristics of analogous pixel regions. Secondly, by utilizing the discrepancy between the minimum and maximum values of infrared and visible images, the proposed technique incorporates the source graph into the fusion process, thereby improving the precision of the information. Additionally, the feature reconstruction function was designed based on the layer features, which could adaptively concentrate the source image information on one image and further improve the clarity and information retention of the fused image. Finally, the results of the qualitative and quantitative comparison of our proposed method with other state-of-the-art methods available, obtained by applying them to public datasets, demonstrated the advantages of our algorithm. Our results retained more appearance details and significantly more target information. [ABSTRACT FROM AUTHOR]

Blind image denoising and edge-preserving are two primary challenges to recover an image from low-level vision to high-level vision. Blind denoising requires a single denoiser can denoise images with any intensity of noise, and it has practical utility since accurate noise levels cannot be acquired from realistic images. On the other hand, edge preservation can provide more image features for subsequent processing which is also important for the denoising. In this paper, we propose a novel blind universal image denoiser to remove synthesis and realistic noise while preserving the image texture. The denoiser consists of noise network and prior network parallelly, and then a fusion block is used to give the weight between these two networks to balance computation cost and denoising performance. We also use the Non-subsampled Shearlet Transform (NSST) to enlarge the size of receptive field to obtain more detailed information. Extensive denoising experiments on synthetic images and realistic images show the effectiveness of our denoiser. [ABSTRACT FROM AUTHOR]

In the Internet of Things (IoT) system for oil field production, oil-well pump leakage is one of the most challenging faults to detect. Once the pump leakage fault occurs, it will severely impact crude oil production. Therefore, accurate diagnosis of oil-well pump leakage faults is highly necessary. However, achieving accurate diagnosis through existing artificial intelligence methods remains a challenge due to the prolonged and progressive nature of oil-well pump leakage faults. This paper proposes a novel methodology for diagnosing oil-well pump leakage. Specifically, we propose a time-series data transformation method that ingeniously transforms difficult-to-identify pump leakage long time-series data variation features into image pixel-level texture features, and based on the characteristics of differences in image texture features under different states, we propose the structure of convolutional residual blocks with attributes and spatial attention for oil-well pump leakage fault diagnosis, which enables more accurate fault diagnosis by assigning more attention weights to extract valuable fault information. Through extensive experimentation, we found that the diagnosis process proposed in this paper outperforms sequence models such as LSTM and GRU, achieving a diagnostic accuracy of 98.36% for oil-well pump leakage faults. Moreover, it leads to a significant improvement of 19.40% and 10.36% in accuracy compared to conventional CNN and ResNet models, respectively. Therefore, in the actual production of oilfields, this method can effectively meet the detection requirements for oil-well pump leakage. • A multivariate time series transformation method for oil well sensor time series data is proposed. • Transformation of time series data into texture features of the image allows for better differentiation of oil well pumps operating states. • An oil-well pump leakage fault diagnosis model with convolutional residual blocks with Attribute and Spatial attention is proposed. [ABSTRACT FROM AUTHOR]

• New texture indices were constructed by texture metrics and effectively used to estimate LAI of maize. • The potential of UAV-based thermal infrared sensor for estimating LAI was proved. • The combination of UAV-based multispectral and thermal infrared data improved the estimation accuracy of LAI. • The RFR model had the strong robustness and achieved the best performance on LAI estimation. Crop leaf area index (LAI) is one of the important indicators to evaluate crop growth and guide field management, and can be used to predict crop yield. Spectral and thermal information extracted by multispectral (MS) and thermal infrared (TIR) sensors mounted on an unmanned aerial vehicle (UAV) can be used for LAI estimation. Image texture is sensitive to the changes in crop surface grayscale or color characteristics, and can be combined with spectral and thermal information to estimate the LAI. But single texture metric has limitations in LAI estimation. Therefore, the purpose of this study is to construct new texture indices based on texture metrics extracted from MS and TIR images, and combined spectral and thermal information to enhance the estimation accuracy of maize LAI. Three replicates of maize experiments under different irrigation treatments were conducted in 2020. The MS and TIR sensors were mounted on a UAV to acquire maize canopy images during critical growth stages and acquire field LAI value of samples synchronously. The LAI estimation models were established using MS data, TIR data, as well as their combination. These models were constructed by Back Propagation Neural Network (BPNN), Partial least squares regression (PLSR), and Random Forest Regression (RFR). Finally, the performance of LAI estimation models was evaluated by the coefficient of determination (R2), root mean square error (RMSE) and relative root mean square error (rRMSE). Results shown that: (i) Among the eight kinds of texture metrics extracted from MS and TIR images, the texture metric mean (MEA) has the best performance. Compared with single texture metrics, texture indices constructed by different metrics has stronger correlation with LAI. (ii) Adding texture indices to estimation models significantly improved model accuracy, especially multispectral three-texture index(MS-TTI) has higher LAI estimation potential than thermal infrared three-texture index(TIR-TTI). (iii) Compared with the use of MS or TIR data alone, the estimation model constructed by combining MS data and TIR data have better performance. The best estimation model obtained by the RFR method (R2 = 0.862, RMSE = 0.246 and rRMSE = 10.20 %) further improved the LAI estimation of maize, with R2 increasing by 6.55 % and 14.48 %, respectively. In conclusion, the combination of MS and TIR data can effectively improve the estimation accuracy of maize LAI, and also provide a feasible method for monitoring crop growth. [ABSTRACT FROM AUTHOR]

• Multi-block data analysis was used for beef quality assessment. • Different parts of beef were evaluated by HSI, 1H NMR and quality parameters datasets. • ComDim shows Clustering results, contribution of data blocks and their relationships. Several factors affect the quality of beef. In the field of chemometrics, multi-block data analysis methods are useful for examining multiple sources of information from a sample. This study focuses on the application of ComDim, a multi-block data analysis method, to evaluate beef from different parts of hyperspectral spectrum and image texture information, 1H NMR fingerprints, quality parameters and electronic nose. Compared to principal component analysis (PCA) methods based on low-level data fusion, ComDim is more efficient and powerful, because it reveals the relationships between the methods and techniques studied, as well as the variability of beef quality across multiple metrics. The quality and metabolite composition of beef tenderloin and hindquarters were differentiated, with low L* value and high shear tenderloin distinguished from hindquarters with opposite characteristics. The proposed strategy demonstrates that ComDim approach can be used to characterize samples when different techniques describe the same set of samples. [ABSTRACT FROM AUTHOR]

• Pavement raveling detection based on image processing is proposed. • Texture analysis techniques are employed for feature extraction. • Two scenarios of GLCM and LBP-GLCM are utilized in the feature extraction stage. • XGBoost classifier is employed for the classification of raveling and no-raveling images. • The results of LBP-GLCM feature extraction achieved better performance for raveling detection. The raveling of asphalt pavement is the primary cause of decreasing road safety, comfort, and service life. Because of the asphalt's complex texture, automatic raveling detection from image samples is a challenging operation. In this study, a computer vision technique, based on image texture features, for automatic detection of asphalt pavement raveling is proposed and verified. Two scenarios are taken into account for feature extraction. First, texture features from images are extracted using the traditional GLCM (Gray-Level Co-occurrence Matrix) algorithm. Second, the images are subjected to LBP (Local Binary Pattern) and then GLCM is employed to extract texture features. Utilizing the eXtreme Gradient Boost (XGBoost) technique, two models are built using the mentioned feature extraction scenarios and then compared. The results indicate that compared to the first scenarios prediction performance (Accuracy, Precision, Recall, and F1-Score are all approximately equal to %81), the second feature extraction scenario can offer higher prediction performance (Accuracy, Precision, Recall, and F1-Score are all approximately equal to %97). In order to demonstrate the model's generalizability, a separate dataset is tested. Due to the acceptable performance values for this dataset (with more than %97 in terms of Accuracy, Precision, Recall, and F1-Score), the suggested model can be beneficial for transportation agencies to enhance the efficiency of road inspection activities. [ABSTRACT FROM AUTHOR]

[Display omitted] • We proposed a unified classification and prediction fusion framework for detecting different types of abnormal events in surveillance videos. • With the assistance of motion features, our AED algorithm is more sensitive to abnormal events in a crowded environment. • Extensive experiments confirm the efficacy and robustness of the proposed framework for AED. • The types of abnormal events on some public AED datasets are analysed, and the accuracies of identifying abnormal events are also counted. Abnormal event detection is a critical component of intelligent surveillance systems, focusing on identifying abnormal objects or unusual human behaviours in video sequences. However, conventional methods struggle due to the scarcity of labelled data. Existing solutions typically train on normal data, establish boundaries for regular events, and identify outliers during testing. These approaches are often inadequate as they do not efficiently leverage the geometry and image texture information, and they lack a specific focus on different types of abnormal events. This paper introduces a novel two-stream fusion algorithm for abnormal event detection to address these diverse abnormal events better. We first extract the object, pose, and optical flow features. Then, the object and pose information is combined early on to eliminate occluded pose graphs. The trusted pose graphs are fed into a Spatio-Temporal Graph Convolutional Network (ST-GCN) to detect abnormal behaviours. Simultaneously, we propose a video prediction framework that identifies abnormal frames by measuring the difference between predicted and ground truth frames. Lastly, we execute a decision-level fusion between the classification and prediction streams to achieve the final results. Our results on the UCSD PED1 dataset indicate the enhanced performance of the fusion model for various abnormal events. Furthermore, experimental results on the UCSD PED2 dataset and the ShanghaiTech campus dataset underscore our approach's effectiveness compared to other related works. [ABSTRACT FROM AUTHOR]

Neutron radiography has been widely employed in nondestructive investigations. The noise and blur that are inevitably generated in the process of neutron radiography seriously decrease the image quality and lead to the loss of image information. In particular, white spot noise, which has the characteristics of nonuniform distribution, large size, and high magnitude, is difficult to remove. To solve this issue, we apply a generative adversarial network-based to convert a degraded neutron image into a clean image. The basic idea is to integrate attention mechanisms into our generation and discrimination networks. A fusion block with a visual attention mechanism is proposed, which can extract more potential features from the images and preserve the image texture as much as possible. In addition, due to the lack of neutron image datasets, we propose a neutron image degradation model to simulate the noise and blur in real neutron images. The results of the experiments show that our method can effectively eliminate noise and blur from neutron images while retaining texture information well. • Proposed a deep learning-based method to remove hybrid noise and blur from neutron images. • A fusion block combines a dense residual block and a spatial channel attention mechanism. • Perceptual loss is used to make our network efficiently learn the high-level information of the image. • Visual evaluation and quantitative analysis illustrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Animals select habitat at multiple spatial scales, suggesting that biodiversity modeling, for example of species richness, should be based on environmental data gathered at multiple spatial scales, and especially multiple grain sizes. Different satellite sensors collect data at different spatial resolutions and therefore provide opportunities for multi-grain habitat measures. The dynamic habitat indices (DHIs), which are derived from satellite data, capture patterns of vegetative productivity and predict bird species richness well. However, the DHIs have only been analyzed at single resolutions (e.g., 1-km), and have not yet been derived from high-resolution satellite data (< 10 -m). Our goal was to predict bird species richness based on measures of vegetation productivity (DHIs, NDVI median and NDVI percentile 90th) across a range of spatial resolutions both from different sensors, and from resampled high-resolution imagery. We analyzed bird species richness within 215 forest, grassland and shrubland plots (56.25 ha) located at 26 terrestrial field sites of the National Ecology Observatory Network (NEON), in the continental US. To obtain our multi-resolution measures of vegetation productivity, we acquired data from Planetscope (3-m), RapidEye (5-m), Sentinel-2 (10-m), Landsat-8 (30-m) and MODIS (250-m) from 2017 to 2020, generated time series of NDVI, calculated the three DHIs (cumulative, minimum and variation), NDVI median and the 90th percentile NDVI and calculated 1st and 2nd order texture measures. We evaluated the performance of the derived measures to predict bird species richness of habitat specialist guilds based on (i) univariate models (ii) multivariate models with single-resolution measures and (iii) multivariate models with multi-resolution measures. Single-spatial resolution measures predicted bird species richness moderately well (R2 up to 0.51) and the best performing spatial resolution and measure differed among bird species guilds. High-spatial resolution (3–5 m) measures outperformed medium-resolution measures (10–250 m). Models for all guilds performed best when incorporating multiple resolutions, including for all species richness (R2 = 0.63) and for forest (R2 = 0.72), grassland (R2 = 0.53) and shrubland specialists (R2 = 0.46). In addition, models based on multi-resolution data from different sensors performed better than models based on resampled high-resolution data for any of the guilds. Our results highlight, first, the value of the DHIs derived from high-resolution satellite data to predict bird species richness and, second, that remotely-sensed vegetation productivity measures from multiple spatial resolutions offer great promise for quantifying biodiversity. • Single-spatial resolution measures predicted bird richness moderately well. • Best-performing spatial resolution and measure differed among bird species guilds. • High-resolution measures performed better than medium-resolution measures. • Multi-grain habitat models performed best for all bird species guilds. • Models based on original data performed better than resampled data models. [ABSTRACT FROM AUTHOR]

Distinguishing malignant from benign lesions has significant clinical impacts on both early detection and optimal management of those early detections. Convolutional neural network (CNN) has shown great potential in medical imaging applications due to its powerful feature learning capability. However, it is very challenging to obtain pathological ground truth, addition to collected in vivo medical images, to construct objective training labels for feature learning, leading to the difficulty of performing lesion diagnosis. This is contrary to the requirement that CNN algorithms need a large number of datasets for the training. To explore the ability to learn features from small pathologically-proven datasets for differentiation of malignant from benign polyps, we propose a Multi-scale and Multi-level based Gray-level Co-occurrence Matrix CNN (MM-GLCM-CNN). Specifically, instead of inputting the lesions' medical images, the GLCM, which characterizes the lesion heterogeneity in terms of image texture characteristics, is fed into the MM-GLCN-CNN model for the training. This aims to improve feature extraction by introducing multi-scale and multi-level analysis into the construction of lesion texture characteristic descriptors (LTCDs). To learn and fuse multiple sets of LTCDs from small datasets for lesion diagnosis, we further propose an adaptive multi-input CNN learning framework. Furthermore, an Adaptive Weight Network is used to highlight important information and suppress redundant information after the fusion of the LTCDs. We evaluated the performance of MM-GLCM-CNN by the area under the receiver operating characteristic curve (AUC) merit on small private lesion datasets of colon polyps. The AUC score reaches 93.99% with a gain of 1.49% over current state-of-the-art lesion classification methods on the same dataset. This gain indicates the importance of incorporating lesion characteristic heterogeneity for the prediction of lesion malignancy using small pathologically-proven datasets. • We propose an adaptive multi-input CNN model for a polyp classification task. • Our strategy uses texture descriptors to explore the voxel heterogeneity of polyps. • We use multi-scale and multi-level GLCM fusion to enhance classification performance [ABSTRACT FROM AUTHOR]

• Image processing tehnique for water surface velocity prediction. • Temporal feature extraction for dynamic image sequence using XOR operator. • Machine learning method for image texture analysis. Water surface velocity (WSV) is one of the critical parameters in hydrology. The development of non-intrusive measurement of this parameter using cameras is increasing. Traditionally, measuring WSV using a camera utilizes tracking of moving objects on the water surfaces. Recently, another method has emerged that utilizes the movement of water ripples to estimate the WSV. This paper proposes a novel method for estimating WSV based on camera measurements. The authors call this method Temporal Gray-scale Pattern Image (TGPI) since it extracts Gray-scale patterns of pixels of water flow video in the temporal domain using the XOR operator and create new image. The new image pattern formed is then used to predict WSV using predictor. There are four predictors being compared, namely Multiple Input Linear Regression (MILR), Multiple Input Logistic Regression (MILgR), Convolutional Neural Network Regression (CNN-R), and Convolutional Neural Network Classification (CNN-K). CNN-R and CNN-K predict WSV directly from the results of TGPI. Meanwhile, MILR and MILgR predict WSV from five TGPI features. The five features are the Mean and Median of the Histogram, Mean and Median of the Histogram of Oriented Gradient (HOG), and the Maximum Mid-Value of the Fast Fourier Transform (FFT). MILR and CNN-R are predictors for regression problems, so the testing metrics for them are Trend-Line equation and R2 from the predicted WSV and actual values graph. Meanwhile, for MILgR and CNN-K, which are predictors for classification problems, the testing metrics are Confusion Matrix (CM), Accuracy, Precision, Recall, and F1-Score. To test the four methods without distinguishing their predictor types, a 2-dimensional histogram graph is used. The data-set used for training and testing is video footage of water flow with known WSV. The WSV measurement points used in this study are 1.7 m/s, 3.1 m/s, and 4.2 m/s. The video dataset and these three points are generated by the Mini Open Channel Water Flow Simulator (MOCWFS) developed by the author in this study. From the comparison results, it can be seen that the classification type predictor is superior to the regression type. For the regression type predictor, MILR is better than CNN-R. Meanwhile, for the classification type, CNN-K is superior to MILgR. The best accuracy produced by CNN-K is 98.4%. Although there are shortcomings, the TGPI method is quite feasible for predict Water Surface Velocity. [ABSTRACT FROM AUTHOR]

Recently, a concept for a new approach for rapid identification of uranium ore concentrate (UOC) powders using colour, textural and spectroscopy signatures was developed using a sample dataset consisting of 79 industrial uranium ore concentrate powders produced by different production routes at different facilities. The samples were first grouped into six different predefined colour categories using a colour-based classification model previously developed. In this study, a machine learning approach was used to develop supervised texture- and spectroscopy-based classification models for each colour category of uranium ore concentrates. Scanning electron microscopy images of the UOC samples were collected at 100x, 250x, 500x/1000× magnifications. A total of 524 texture features describing sample morphology were extracted from each image using First Order Statistics (FOS), Grey Level Co-Occurrence Matrix (GLCM), Grey Level Run Length Matrix (GLRLM), Grey Level Size Zone Matrix (GLSZM), Locally Binary Pattern (LBP) and Angle Measure Technique (AMT) textural feature extraction algorithms. Hyperspectral images of the samples were collected in the wavelength range 900–1700 nm and the mean spectrum of each sample was calculated, giving the spectral features of the UOCs. The texture and spectral features were used as input to the machine learning approach which consisted of a feature reduction step to identify discriminatory features and a classification step to provide the texture- and spectroscopy-based models. An average prediction accuracy of 82% and 97% were obtained for the texture- and spectral-based classification models, respectively, on hold-out test sets. The feature reduction step identified two new nuclear forensics signatures, consisting of 3–7 texture (morphological) characteristics and 2–6 characteristic wavelengths, respectively. This new approach enables rapid classification of unknown uranium ore concentrate powders using only their textural and hyperspectral images. By combining the classification results from the two models, the most probable production process and chemical composition can be identified, and the provenience of the seized sample can be narrowed down to a few matching possibilities. Moreover, after the image acquisition, the models can provide results in less than 2 min speeding up the investigation procedure, a key factor when a nuclear security event occurs. • A new approach to classify seized UOCs powders by colour, texture and spectroscopy data is proposed. • 79 commercial UOCs samples were used as training and test samples. • ML approach was used to test several classifiers and to carry out feature reduction/selection. • LDA was selected as the most promising classifier to develop the texture/spectroscopy-based classification models. • An average prediction accuracy of 82% and 97% were obtained for the two models respectively. [ABSTRACT FROM AUTHOR]

Defrost control using digital image processing is a potential, economical, and energy-saving solution for air-source heat pump or refrigeration system, comparing with currently studied or used direct/indirect measuring methods. However, under complex operating condition of different shooting angles, lighting conditions, and pixel level, which are common in refrigeration system, the accuracy of frost state recognition with existing digital image processing methods decrease dramatically. Therefore, a new method based on optimized gray level co-occurrence matrix and new characterization parameter combination to extract image texture characteristics, combining extreme learning machine algorithm (OGLCM-ELM), is proposed for the first time. An experimental rig for evaporator frosting image under different lighting intensity, shooting angle and pixel level is set up. The collected experimental image data are divided into 3 classifications (Frostless, light frost, and heavy frost) or 2 classifications ((Frostless + light frost, and heavy frost)). The results show for ternary classification, OGLCM-ELM reveals significantly higher recognition accuracy then existing methods, average accuracy is as higher as 98.14%. It is also 5.28% and 3.14% higher than those of OGLCM-SVM, OGLCM-BP. Other performance parameters, precision, recall, F1-score, and calculating time are also totally better than other methods. For binary classification. the average accuracy of OGLCM-ELM even reaches 99% under complex operating condition, indicating it is a practical and potential technology for defrost control. [ABSTRACT FROM AUTHOR]

• DLR images achieve substantial noise reduction compared with other reconstruction algorithms. • DLR images maintain noise texture better than other reconstruction algorithms. • Sole phantom studies are insufficient for future evaluation of DLR techniques. To compare the noise power spectrum (NPS) properties and perform a qualitative analysis of hybrid iterative reconstruction (IR), model-based IR (MBIR), and deep learning–based reconstruction (DLR) at a similar noise level in clinical study and compare these outcomes with those in phantom study. A Catphan phantom with an external body ring was used in the phantom study. In the clinical study, computed tomography (CT) examination data of 34 patients were reviewed. NPS was calculated from DLR, hybrid IR, and MBIR images. The noise magnitude ratio (NMR) and the central frequency ratio (CFR) were calculated from DLR, hybrid IR, and MBIR images relative to filtered back-projection images using NPS. Clinical images were independently reviewed by two radiologists. In the phantom study, DLR with a mild level had a similar noise level as hybrid IR and MBIR with strong levels. In the clinical study, DLR with a mild level had a similar noise level as hybrid IR with standard and MBIR with strong levels. The NMR and CFR were 0.40 and 0.76 for DLR, 0.42 and 0.55 for hybrid IR, and 0.48 and 0.62 for MBIR. The visual inspection of the clinical DLR image was superior to that of the hybrid IR and MBIR images. Deep learning–based reconstruction improves overall image quality with substantial noise reduction while maintaining image noise texture compared with the CT reconstruction techniques. [ABSTRACT FROM AUTHOR]

3D ground penetrating radar is the main detection technology used to locate underground targets on urban roads, and the current underground target intelligent identification algorithms for this technology rely on two-dimensional images. Relying only on radar image texture as the identification feature, due to the limitations of single dimensionality and single feature utilization, leads to significant errors of these algorithms in identifying underground targets. For the above problems, an underground target depth time-frequency statistical feature identification algorithm based on 3D convolution using raw radar data is proposed. The detailed changes and overall trends of underground targets are extracted by multi-size 3D receptive fields. Meanwhile, the depth time-frequency statistical features of multiple position slices in the horizontal, vertical, crossed-vertical, left-right diagonal, and front-back diagonal directions of radar data are constructed at different layers. Multi-dimensional time-frequency statistical features are input to a fully connected classifier, and the final result is obtained by combining the classification results of the seven directions through the Bagging mechanism. This algorithm expands the feature dimension and direction of judging underground targets and strengthens the feature representation ability. It makes full use of the 3D ground penetrating radar data information and reflects the features of underground space from multiple angles, which improves the identification accuracy of underground targets. • A 3D GPR classification algorithm using statistical features is proposed. • Time-frequency features from radar data are used to train the algorithm. • Multi-scale receptive field 3D convolution to extract feature. • Using multi-direction data features to reflect the underground target. • Using the Bagging thought to combine the advantages of multi-angle features. [ABSTRACT FROM AUTHOR]

• Texture parameters of the composites contain the information about their durability. • Machine learning algorithms used for the assessment of hydrophobization efficiency. • Microstructural properties of hydrophobic coatings modified by nanocellulose. The aim of the study was to determine a set of image texture features of the lightweight cementitious composites (LLC) with hydrophobic coatings modified with nanocellulose and use them to assess the materials' durability. A novel method based on a combination of image texture analysis and machine learning methods was proposed. Textural features were extracted from the images obtained with a scanning microscope. The best classification model was built by the Support Vector Machine method using 16 features selected by the Sequential Forward Selection algorithm. The model recognizes one of the four ranges of the contact angle, which is closely related to the degree of resistance of the analyzed material, with an accuracy of 82%. The results obtained show a relationship between the effectiveness of hydrophobic coatings in LCC and images of their surfaces. This relationship can be used with machine learning methods for conducting strength diagnostics of building materials. [ABSTRACT FROM AUTHOR]

• Texture features of hydrophobized concrete contain the information about their absorptivity. • Machine learning algorithms are used to estimate the absorptivity of hydrophobic concrete. • Water absorption of concrete is reliably estimated from conventional SEM. • Application of image texture analysis to characterize the condition of hydrophobic concrete surfaces. The work concerned the study of surface hydrophobized concrete's physical and mechanical properties. An aqueous emulsion based on nano-silicates (A1) and an oligomeric propylsilicate/silicate (A2) concentrate in three dilution states (100%, 70%, and 50%) were used as surface modification agents. The scanning electron microscopy (SEM) images determined three classes of water absorption (WA). A predictive modeling process was performed to automatically identify 1 of the 3 water absorption classes. For the best model, a classification accuracy of 96% was obtained. After 14 days of testing, the hydrophobization efficiency was still high, over 54% for A1 and 45% for A2 for 100% concentration. The samples achieved the best frost resistance with agents A1 and A2 in a 70% concentration. Experimental studies have confirmed the close relationship between concretes' water absorptivity and their surfaces' SEM images. No similar studies of this type are known. [ABSTRACT FROM AUTHOR]