Search

Land cover mapping is an important part of resource management, planning, and economic predictions. Improvements in remote sensing, machine learning, image processing, and object based image analysis (OBIA) has made the process of identifying land cover types increasingly faster and reliable but these advances have not been able to utilize all of the information encompassed within ultra-high (sub-meter) resolution imagery. There have been few known attempts to try and maximize this detailed information in high resolution imagery using advanced textural components. Hierarchical land classes are also rarely used as an attribute within the machine learning step of object-based image analysis. In this study we try to circumnavigate the inherent problems associated with high resolution imagery by combining well researched data transformations that aid the OBIA process with a seldom used texture transformation in Geographic Object Based Image Analyses (GEOBIA/OBIA) known as the Gabor Transform and the hierarchal organization of landscapes. We will observe the difference made in segmentation and classification accuracy of a random forest classifier when we fuse a Gabor transformed image to a Normalized Difference Vegetation Index (NDVI), high resolution multi-spectral imagery (RGB and NIR) and Light Detection and Ranging (LiDAR) derived canopy height model (CHM) within a riparian area in Southeast Iowa, United States. Additionally, we will observe the effects on classification accuracy when adding multi-scale land cover data to objects. Both, the addition of hierarchical information and Gabor textural information, could aid the GEOBIA process in delineating and classifying the same objects that human experts would delineate within this riparian landscape. [ABSTRACT FROM AUTHOR]

The alternative starches and flours used in gluten-free bakery in replacement of wheat have very low quantities of fibre. As a consequence, the resulting products have a poor nutritional profile in terms of this nutrient, and present technological difficulties and quality challenges related to texture. In this work, the texture of gluten-free cookies added with a source of fibre, and its impact in consumer's perception was studied. Due to the complexity of texture, its description was assessed through three different methods: instrumental force/deformation measurements, image analysis, and sensory evaluation, in order to reach a better representation of the product's texture and to compare the different techniques' capacity to describe it. The instrumental method showed that the control cookie presented a higher maximum force (Fmax), indicating that this sample was significantly more resistant to fracture, while the cookie added with fibre showed a lower deformation before fracture (ΔFmax), which corresponds to a more fragile structure. The results obtained by image texture analysis using the Gray Level Co-occurrence Matrix method were consistent with those determined by instrumental analysis. Good correlations were reached between the instrumental firmness and the five image parameters, showing the capacity of image attributes to predict mechanical properties of the samples. Sensory analysis with consumers showed a good acceptability of the product, but was not as useful to detect small differences between cookies. The study of texture through different techniques could be an interesting approach to attain complementary information, providing a more comprehensive perspective of this multifaceted attribute. [ABSTRACT FROM AUTHOR]

Goblet cells (GCs) in the conjunctiva are specialized epithelial cells secreting mucins for the mucus layer of protective tear film and playing immune tolerance functions for ocular surface health. Because GC loss is observed in various ocular surface diseases, GC examination is important for precision diagnosis. Moxifloxacin-based fluorescence microscopy (MBFM) was recently developed for non-invasive high-contrast GC visualization. MBFM showed promise for GC examination by high-speed large-area imaging and a robust analysis method is needed to provide GC information. In this study, we developed a deep learning framework for GC image analysis, named dual-channel attention U-Net (DCAU-Net). Dual-channel convolution was used both to extract the overall image texture and to acquire the GC morphological characteristics. A global channel attention module was adopted by combining attention algorithms and channel-wise pooling. DCAU-Net showed 93.1% GC segmentation accuracy and 94.3% GC density estimation accuracy. Further application to both normal and ocular surface damage rabbit models revealed the spatial variations of both GC density and size in normal rabbits and the decreases of both GC density and size in damage rabbit models during recovery after acute damage. The GC analysis results were consistent with histology. Together with the non-invasive high-contrast imaging method, DCAU-Net would provide GC information for the diagnosis of ocular surface diseases. [ABSTRACT FROM AUTHOR]

Machine learning, and especially deep learning, is rapidly gaining acceptance and clinical usage in a wide range of image analysis applications and is regarded as providing high performance in detecting anatomical structures and identification and classification of patterns of disease in medical images. However, there are many roadblocks to the widespread implementation of machine learning in clinical image analysis, including differences in data capture leading to different measurements, high dimensionality of imaging and other medical data, and the black-box nature of machine learning, with a lack of insight into relevant features. Techniques such as radiomics have been used in traditional machine learning approaches to model the mathematical relationships between adjacent pixels in an image and provide an explainable framework for clinicians and researchers. Newer paradigms, such as topological data analysis (TDA), have recently been adopted to design and develop innovative image analysis schemes that go beyond the abilities of pixel-to-pixel comparisons. TDA can automatically construct filtrations of topological shapes of image texture through a technique known as persistent homology (PH); these features can then be fed into machine learning models that provide explainable outputs and can distinguish different image classes in a computationally more efficient way, when compared to other currently used methods. The aim of this review is to introduce PH and its variants and to review TDA's recent successes in medical imaging studies. Key points: Topological data analysis (TDA) provides information on the shape of data. In radiology, the shape of 2D and 3D images contains additional information. TDA can be combined with other applications, such as textural analysis. Persistent homology can provide a visual representation of extracted TDA data. [ABSTRACT FROM AUTHOR]

Fresh grapes are characterized by a short shelf life and are often subjected to quality losses during post-harvest storage. The quality assessment of grapes using image analysis may be a useful approach using non-destructive methods. This study aimed to compare the effect of different storage methods on the grape image texture parameters of the fruit outer structure. Grape bunches were stored for 4 weeks using 3 storage methods (– 18 °C, + 4 °C, and room temperature) and then were subjected subsequently to image acquisition using a flatbed scanner and image processing. The models for the classification of fresh and stored grapes were built based on selected image textures using traditional machine learning algorithms. The fresh grapes and stored fruit samples (for 4 weeks) in the freezer, in the refrigerator and in the room were classified with an overall accuracy reaching 96% for a model based on selected texture parameters from images in color channels R, G, B, L, a, and b built using Random Forest algorithm. Among the individual color channels, the carried-out classification for the R color channel produced the highest overall accuracies of up to 92.5% for Random Forest. As a result, this study proposed an innovative approach combining image analysis and traditional machine learning to assess changes in the outer structure of grape berries caused by different storage conditions. [ABSTRACT FROM AUTHOR]

With the continuous progress of science and technology, image processing techniques have been used increasingly in recent years. Image processing plays an indispensable role in the fields of computer vision, artificial intelligence, pattern recognition, and related fields. Improvements in basic algorithms and the development of new algorithms have resulted in considerable innovation and progress. This paper is devoted to finding new game applications in a branch of image processing. It introduces an analysis model proposed by the author and discusses the relationship between roughness in the frequency domain and visual image interpretation. By using the concept of roughness, we separated the image features into meaningful information and residual information and analysed the image in the frequency domain. The results were compared with those of traditional image processing methods. The starting point is the visual identification of a feature based on human interpretation. The image information was separated into meaningful features and the residual component to reduce the redundancy of the model. This allowed for a sparse representation of the feature information in the image. By analysing the meaningful features and residual components of an image separately, we established a relationship between the results and the original images. Parameters such as texture, morphology, and the degree of blurring were considered and we developed a parameter called "frequency roughness". The algorithm incorporates the concepts of frequency and roughness and the roughness is determined in the frequency domain. The frequency roughness algorithm successfully separated the rough features in the frequency domain and calculated the residual value in an image. This model provided more accurate image processing results than comparable methods. This paper includes an analysis and game applications of the proposed model for de-blurring, image enhancement, recognition, and other image processing tasks. Some game applications were successful, whereas others require further investigation. [ABSTRACT FROM AUTHOR]

Due to the nature of Selective Laser Melting process, the built parts suffer from high chances of defects formation. Powders quality have a significant impact on the final attributes of SLM-manufactured items. From a processing standpoint, it is critical to ensure proper powder distribution and compaction in each layer of the powder bed, which is impacted by particle size distribution, packing density, flowability, and sphericity of the powder particles. Layer-by-layer study of the process can provide better understanding of the effect of powder bed on the final part quality. Image-based processing technique could be used to examine the quality of parts fabricated by Selective Laser Melting through layerwise monitoring and to evaluate the results achieved by other techniques. In this paper, a not supervised methodology based on Digital Image Processing through the build-in machine camera is proposed. Since the limitation of the optical system in terms of resolution, positioning, lighting, field-of-view, many efforts were paid to the calibration and to the data processing. Its capability to individuate possible defects on SLM parts was evaluated by a Computer Tomography results verification. [ABSTRACT FROM AUTHOR]

The present research study aimed to examine three different herb extract's effects on the discoloration rate of fresh-cut pear slices using an image analysis technique. Pear slices were sprayed and dip-coated with Ocimum basilicum, Origanum vulgare, and Camellia sinensis (0.1 g/ml) extract solution. During 15 days storage period with three days intervals, all sprayed/dip-coated pear slices were analyzed for the quality attribute (TA) and color parameters notably a*, b*, hue angle (H*), lightness (L*), and total color change (ΔE). Further, order kinetic models were used to observe the color changes and to predict the shelf-life. The results obtained showed that the applicability of image analysis helped to predict the discoloration rate, and it was better fitted to the first-order (FO) kinetic model (R2 ranging from 0.87 to 0.99). Based on the kinetic model, color features ΔE and L* was used to predict the shelf-life as they had high regression coefficient values. Thus, the findings obtained from the kinetic study demonstrated Camellia sinensis (assamica) extract spray-coated pear slices reported approximately 28.63- and 27.95-days shelf-stability without much discoloration compared with all other types of surface coating. [ABSTRACT FROM AUTHOR]

General methods of image processing, analysis and enhancement and their biomedical applications developed by the scientific school of the Laboratory of Mathematical Methods of Image Processing of the Faculty of Computational Mathematics and Cybernetics of Lomonosov Moscow State University are reviewed. The suggested general methods and algorithms of image quality enhancement for image resampling and super-resolution, ringing artifact reduction, image sharpening, image denoising, and image registration are described. Image analysis methods based on Hermite projection method, Gauss-Laguerre functions and the use of phase information are presented. We describe and review the developed methods for medical imaging tasks solution, including problems in histology, color Doppler flow mapping, ultrasound liver fibrosis diagnostics, CT brain perfusion, Alzheimer's disease diagnostics, dermatology, chest X-ray image analysis, live cell image registration, tracking, segmentation and synthesis. The paper illustrates the basic research idea of the effectiveness of the hybrid approach when we jointly use classical mathematical methods and deep learning approaches. [ABSTRACT FROM AUTHOR]

Apparent diffusion coefficient (ADC) of magnetic resonance imaging (MRI) is an indispensable imaging technique in clinical neuroimaging that quantitatively assesses the diffusivity of water molecules within tissues using diffusion-weighted imaging (DWI). This study focuses on developing a robust machine learning (ML) model to predict the aggressiveness of gliomas according to World Health Organization (WHO) grading by analyzing patients' demographics, higher-order moments, and grey level co-occurrence matrix (GLCM) texture features of ADC. A population of 722 labeled MRI-ADC brain image slices from 88 human subjects was selected, where gliomas are labeled as glioblastoma multiforme (WHO-IV), high-grade glioma (WHO-III), and low-grade glioma (WHO I-II). Images were acquired using 3T-MR systems and a region of interest (ROI) was delineated manually over tumor areas. Skewness, kurtosis, and statistical texture features of GLCM (mean, variance, energy, entropy, contrast, homogeneity, correlation, prominence, and shade) were calculated using ADC values within ROI. The ANOVA f-test was utilized to select the best features to train an ML model. The data set was split into training (70%) and testing (30%) sets. The train set was fed into several ML algorithms and selected most promising ML algorithm using K-fold cross-validation. The hyper-parameters of the selected algorithm were optimized using random grid search technique. Finally, the performance of the developed model was assessed by calculating accuracy, precision, recall, and F1 values reported for the test set. According to the ANOVA f-test, three attributes; patient gender (1.48), GLCM energy (9.48), and correlation (13.86) that performed minimum scores were excluded from the dataset. Among the tested algorithms, the random forest classifier(0.8772 ± 0.0237) performed the highest mean-cross-validation score and selected to build the ML model which was able to predict tumor categories with an accuracy of 88.14% over the test set. The study concludes that the developed ML model using the above features except for patient gender, GLCM energy, and correlation, has high prediction accuracy in glioma grading. Therefore, the outcomes of this study enable to development of advanced tumor classification applications that assist in the decision-making process in a real-time clinical environment. [ABSTRACT FROM AUTHOR]

Mealiness is a phenomenon in which intercellular adhesions in apples loosen during storage, causing a soft and floury texture at the time of eating, and leading to lower consumer preference. Although apples can be stored and commercially sold throughout the year, the occurrence of mealiness is not monitored during storage. Therefore, the objective of this research was to non-destructively estimate the mealiness of apple fruit by means of laser scattering measurement. This method is based on laser light backscattering imaging but can quantify a wider range of backscattered light than the conventional method by utilizing high dynamic range (HDR) rendering techniques. Lasers with wavelengths of 633 nm and 850 nm were used as a light source, and after acquiring backscattered images, profiles, and images were obtained. Profile features such as curve fitting coefficients and profile slopes and image features such as statistical image features and texture features were extracted from the profiles and images, respectively. PLS, SVM, and ANN models were used for the estimation of mealiness. The results of the estimation based on these features showed that the ANN model combining both wavelengths had a higher performance (R = 0.634, RMSE = 7.621) than the models constructed from features of single wavelength measurements. In order to further improve the performance of the model, we applied various ensemble learning methods to combine different estimation models. As a result, the ensemble model showed the highest performance (R = 0.682, RMSE = 7.281). These results suggest that laser scattering measurement is a promising method for estimating apple fruit mealiness. [ABSTRACT FROM AUTHOR]

The endoscopic examination of subepithelial vascular patterns within the vocal fold is crucial for clinicians seeking to distinguish between benign lesions and laryngeal cancer. Among innovative techniques, Contact Endoscopy combined with Narrow Band Imaging (CE-NBI) offers real-time visualization of these vascular structures. Despite the advent of CE-NBI, concerns have arisen regarding the subjective interpretation of its images. As a result, several computer-based solutions have been developed to address this issue. This study introduces the CE-NBI data set, the first publicly accessible data set that features enhanced and magnified visualizations of subepithelial blood vessels within the vocal fold. This data set encompasses 11144 images from 210 adult patients with pathological vocal fold conditions, where CE-NBI images are annotated using three distinct label categories. The data set has proven invaluable for numerous clinical assessments geared toward diagnosing laryngeal cancer using Optical Biopsy. Furthermore, given its versatility for various image analysis tasks, we have devised and implemented diverse image classification scenarios using Machine Learning (ML) approaches to address critical clinical challenges in assessing laryngeal lesions. [ABSTRACT FROM AUTHOR]

All currently known methods and ways for the formation of the fractal features of polarimetric radar images have been given. A new textural-fractal feature has been briefly considered: a directional multifractal signature measured morphologically by an iterative coverage method. In relation to the analysis of polarimetric images generated by a synthetic aperture radar, a new concept of their processing based on the possibility of considering the polarization differences of terrestrial spatially distributed objects by identifying the multifractal and anisotropic properties of their texture has been proposed. The variant of interpretation of the results for automation of further successful solution of specific problems of segmentation (classification) of the underlying surface and detection and recognition of ground objects has been shown. [ABSTRACT FROM AUTHOR]

High-quality histopathology images are significant for accurate diagnosis and symptomatic treatment. However, local cross-contamination or missing data are common phenomena due to many factors, such as the superposition of foreign bodies and improper operations in obtaining and processing pathological digital images. The interpretation of such images is time-consuming, laborious, and inaccurate. Thus, it is necessary to improve diagnosis accuracy by reconstructing pathological images. However, corrupted image restoration is a challenging task, especially for pathological images. Therefore, we propose a multi-scale self-attention generative adversarial network (MSSA GAN) to restore colon tissue pathological images. The MSSA GAN uses a self-attention mechanism in the generator to efficiently learn the correlations between the corrupted and uncorrupted areas at multiple scales. After jointly optimizing the loss function and understanding the semantic features of pathology images, the network guides the generator in these scales to generate restored pathological images with precise details. The results demonstrated that the proposed method could obtain pixel-level photorealism for histopathology images. Parameters such as RMSE, PSNR, and SSIM of the restored image reached 2.094, 41.96 dB, and 0.9979, respectively. Qualitative and quantitative comparisons with other restoration approaches illustrate the superior performance of the improved algorithm for pathological image restoration. [ABSTRACT FROM AUTHOR]

Breast tumor segmentation and recognition from mammograms play a key role in healthcare and treatment services. As different tumors in mammography have dissimilar densities, shapes, sizes, and edges, the interpretation of mammograms can be time-consuming and prone to interpretation variability even for a highly trained radiologist or expert. In this study, several encoding approaches are first proposed to achieve an effective breast cancer recognition system as well as create new images from the input image. Each encoded image represents some unique features that are crucial for detecting the target texture properly. Subsequently, pectoral muscle is eliminated using obtained features from these encoded images. Moreover, 11 distinct images are then applied to a shallow and efficient cascade Convolutional Neural Network (CNN) for classifying each pixel inside the image. This network accepts 11 local patches as the input from 11 obtained encoded images. Next, all extracted features are concatenated to a vertical vector to apply to the fully connected layers. Using different representations of the input mammogram images, the suggested model is able to analyze the input texture more effectively without using a deep CNN model. Finally, comprehensive experiments are then conducted on two public datasets which then demonstrate that the proposed framework successfully is able to gain competitive outcomes compared to a number of baselines. [ABSTRACT FROM AUTHOR]

Fractional calculus is an important branch of mathematical analysis and played a fundamental role in different fields including signal processing and image processing. In this paper, we proposed a sparse super-resolution (SR) technique by using the Grünwald-Letnikov (G–L) fractional differential operator, which aims to reconstruct high-resolution images by recovering pixel information from low-resolution images. We suggested a modified fractional derivative mask based on G–L for image enhancement. The proposed method suppresses block artifacts, staircase edges, and false edges near the edges. The proposed method is very flexible and preserves detailed features. The obtained experiments demonstrated that fractional operator can nonlinearly preserve the low-frequency contour information in the smooth region and also nonlinearly improve well the high-frequency edge and texture of the image. In sparse SR images, the dictionary is constructed by texture information of the images by using integer derivatives. In this work, we computed dictionary matrices by applying the fractional masks. In fact, the extracted features based on fractional derivatives are utilized in the dictionary training procedure and sparse coding. The experimental results and analysis on natural images indicated that the proposed method achieved much better results than other algorithms in terms of both quantitative measures and visual perception. [ABSTRACT FROM AUTHOR]

Segmenting retinal blood vessels from retinal images is a crucial step in ocular disease diagnosis. It is also one of the most important applications and research in ophthalmic image analysis. However, the contrast between the retinal vessels and background in fundus images is low. The size and shape of retinal vessels vary significantly, and the width of some small vessels is often below 10 pixels or even 1 pixel. Moreover, some blood vessels are discontinuous owing to illumination, which complicates the segmentation of retinal blood vessels. To address these problems, this paper innovatively proposes a novel retinal vessel segmentation network framework based on self-distillation and implicit neural representation, which predicts retinal vessels in two stages. First, the self-distillation method extracts the main features of retinal images using the properties of Vision Transformer (ViT) to obtain preliminary images for the blood vessel segmentation. Second, implicit neural representation improves the resolution of the original retinal image, and the details of blood vessels are enhanced through the texture enhancement module to obtain accurate results of the blood vessel segmentation. Furthermore, we adopted an improved centerline dice (clDice) loss function to constrain the topology of blood vessels. We experimented on two benchmark retinal datasets (i.e., Drive and Chase) to quantitatively and qualitatively analyze the proposed method. The results indicate that the proposed outperformed the mainstream baseline. The visual segmentation results also show that this method can segment thin blood vessels more accurately and ensure the continuity of blood vessels. [ABSTRACT FROM AUTHOR]

Medical ultrasound imaging technology is currently the preferred method for early diagnosis of thyroid nodules. Radiologists' analysis of ultrasound images is highly dependent on their clinical experience and is susceptible to intra- and inter-observer variability. Although end-to-end deep learning technique can address these limitations, the difficulty of acquiring annotated medical image makes it very challenging. Transfer learning can alleviate the problems, but the large gap between source and target domain will lead to negative transfer. In this paper, a novel transfer learning method with distant domain high-level feature fusion (DHFF) model is proposed. It reduces the distribution distance between the source domain and the target domain while maintaining the characteristics of respective domains, which can avoid excessive feature fusion while enabling the model to learn more valuable transfer knowledge. The DHFF is validated by multiple public source and private target datasets in experiments. The results show that the classification accuracy of DHFF is up to 88.92% with thyroid ultrasound auxiliary source domains, which is up to 8% higher than existing transfer and distant transfer algorithms. [ABSTRACT FROM AUTHOR]

The digital image proves critical evidence in the fields like forensic investigation, criminal investigation, intelligence systems, medical imaging, insurance claims, and journalism to name a few. Images are an authentic source of information on the internet and social media. But, using easily available software or editing tools such as Photoshop, Corel Paint Shop, PhotoScape, PhotoPlus, GIMP, Pixelmator, etc. images can be altered or utilized maliciously for personal benefits. Various active, passive and other new deep learning technology like GAN approaches have made photo-realistic images difficult to distinguish from real images. Digital image tamper detection now focuses on determining the authenticity and consistency of digital photos. The major research problems use generic solutions and strategies, such as standardized data sets, benchmarks, evaluation criteria and generalized approaches.This paper overviews the evaluation of various image tamper detection methods. A brief discussion of image datasets and a comparative study of image criminological (forensic) methods are included in this paper. Furthermore, recently developed deep learning techniques along with their limitations have also been addressed. This study aims to comprehensively analyze image forgery detection methods using conventional and advanced deep learning approaches. [ABSTRACT FROM AUTHOR]

In unstructured agricultural environments, accurate fruit detection and picking point localization are important for automatic robotic harvesting. In order to solve the machine vision problem of selective mechanized picking of clustered fruit, this study proposed a novel vision algorithm for target recognition and picking point localization based on the shape and growth characteristics of clustered tomatoes. The picking point has to be determined according to its position and posture relative to the fruit or fruit cluster. The shape, texture and color features of tomatoes were extracted and combined to realize accurate tomato recognition. The precision, recall and accuracy of the recognition model were as high as 100%, and the recognition time was less than 1 s. After the recognition of tomato fruit area, this study further developed a two-step picking point positioning algorithm. Firstly, the co-ordinates and radius of the fruit center of mass was acquired, and then the contour line of the whole bunch of fruits were fitted based on Hough circle detection. Secondly, spatially symmetrical spline interpolation method and geometric analysis were applied for peduncle estimation, contour fitting and picking point location. Experimental results showed that located picking points were distributed on the branches, and the position deviation was small, which met the requirements within a certain positioning accuracy range. This indicated that the proposed method can achieve satisfactory picking-points location effect of clustered fruit in complex environments. [ABSTRACT FROM AUTHOR]

Image segmentation refers to analysis of the images to understand its content, and now it is a very promising field of image processing and computer vision. The key objective of this study is to acquire optimal boundary lines to obtain the segmented images from heterogeneous datasets by tuning few relevant parameters of whale optimization algorithm (WOA) with long short-term memory (LSTM) network for heterogeneous datasets. In this paper, the LSTM has been explored to overcome the vanishing gradient problem of recurrent neural network (RNN) and the usefulness of stacked form of LSTM has been used to explore the depth of LSTM network which are more important than the number of memory cells given in a layer to model the skill. This study has been experimented with two LSTMs in a stacked form which provides a sequence output rather than a single value output to the LSTM layer below. Specifically, one output per input time step, rather than one output time step for all input time steps, is used to obtain the optimal and finer boundaries. The proposed tuned WOA hybridized with stacked form of LSTM for digital image segmentation strategy has been coined as S-LSTM-TWOA. The performance of the proposed model has been compared with hybridized S-LSTM network with genetic algorithm, particle swarm optimization, WOA and binary WOA techniques. The execution performance with respect to convergence speed, accuracy, execution time, Dice coefficient, intersection over union (IoU) is also recorded. The overall performance shows the segmentation capability of the proposed S-SLTM-TWOA to be more promising than the compared model by achieving approximately 99%, 99% and 98% for satellite images, BCN 20,000 and RVC 2020 datasets. [ABSTRACT FROM AUTHOR]

Chickpea is an important edible legume that can be grown in rain fed conditions. Image analysis and machine learning could be used for rapid and non-destructive determination of seed physical attributes and such techniques yield objective, accurate and reliable results. In this study, size, shape, and area attributes of 26 different chickpea cultivars were determined by image processing method, and color properties were determined by chromametric method, and machine learning algorithms (Multilayer Perceptron-MLP, Random Forest-RF, Support Vector Regression-SVR, and k-Nearest Neighbor-kNN, were used for mass prediction of chickpea seeds. Ilgaz and Çakır cultivars had the highest size and shape values, while İzmir and Sezenbey cultivars had the highest color attributes. Compactness (in horizontal orientation) had a positive correlation with the equivalent diameter (in vertical orientation) and elongation (in vertical orientation) (r = 0.99 for both parameters). Besides, a* had a high correlation with b* (r = 0.97). According to Euclidean distances, Akça–İnci and Damla–Işık cultivars were identified as the closest cultivars in terms of physical attributes. In PCA analysis, PC1 and PC2 explained 73.17% of the total variation. The PC1 included length, geometric mean diameter, volume and surface area, and the PC2 included roundness (in horizontal orientation), thickness, elongation (in horizontal orientation) and sphericity. RF and ML had successful results with the values of 0.8054 and 0.8043 for train-test split, and 0.8231 and 0.8142 for k-fold cross validation, respectively. Present findings revealed that texture image processing and machine learning could be used as an effective and inexpensive discrimination tool for chickpea seeds. [ABSTRACT FROM AUTHOR]

In this paper, Legendre wavelet transform–based texture analysis is proposed to study the phase transitional characteristics of hydrogen-bonded liquid crystals. Optical textures are the essential features of liquid crystals and analysis of these textural features is useful to investigate the material characteristics. Hydrogen-bonded liquid crystals: alkyl benzoic acid: p-(p′-Octyloxybenzylidene)-p-cyano aniline (nBA:OBCA, n = 6, 7, 8) are considered for investigation. Intermolecular interactions between the mesogen p-n- alkyl benzoic acid (nBA) and mesogenic compound p-(p′-Octyloxybenzylidene)-p-cyano aniline (OBCA) yield the hydrogen-bonded liquid crystals nBA:OBCA. Here, Legendre moments are computed from the wavelet-transformed optical texture using MATLAB computational tool. As a function of temperature, the phase transformations of liquid crystal from crystalline phase to isotropic liquid phase and vice versa can be observed as series of liquid crystal textures using polarizing optical microscope. All these textures show some variations in their features with respect to temperature and most of these variations can be observed as sudden or abnormal changes in transmitted intensity values of textures. They influence the moment values which are computed from the gray level transmitted intensities. Legendre wavelet transform captures the texture information in both frequency and spatial domains. And analysis of this information is useful to study phase behavior of liquid crystals. The results of the proposed methodology are in good agreement with thermal techniques available in the literature. [ABSTRACT FROM AUTHOR]

The denoising of brain magnetic resonance images could be important for the medical image analysis. Many algorithms have been proposed for this task, especially the deep learning ones which show great success compared with the classical image processing algorithms. Though satisfied results it achieve, they may fail to consider the contextual and attentive features during the feature learning process, and those ones could provide essential and complementary information for the feature encoding, and the poor learning of them could hinder the model to achieve a better performance. To address this challenge, in this paper, we propose a multi-dilated block (MDB) which aims to extract more contextual and attentive features during the feature extraction stage. The whole network is based on DnCNN, and the MDB is placed in the middle stage of the network to learn the contextual and attentive representations. Moreover, for improving the similarity between the noisy image and the denoised one from feature-level, we propose a perceptual loss which is able to further boost the performance of the MDB network. To validate the effectiveness of our proposed method, we conduct extensive experiments on the brain magnetic resonance images to compare the peak signal to noise ratio and structural similarity index, and the final experimental results demonstrate that our propose method could predict a higher resolution image compared with other ones. [ABSTRACT FROM AUTHOR]

The automated magnetic resonance imaging (MRI) processing techniques are gaining more importance in Alzheimer disease (AD) recognition, because it effectively diagnosis the pathology of the brain. Currently, computer aided diagnosis based on image analysis is an emerging tool to support AD diagnosis. In this research study, a new system is developed for enhancing the performance of AD recognition. Initially, the brain images were acquired from three online datasets and one real-time dataset such as AD Neuroimaging Initiative (ADNI), Minimal Interval Resonance Imaging in AD (MIRIAD), and Open Access Series of Imaging Studies (OASIS) and National Institute of Mental Health and Neuro Sciences (NIMHANS). Then, adaptive histogram equalization (AHE) and grey wolf optimization based clustering algorithm (GWOCA) were applied for denoising and segmenting the brain tissues; grey matter (GM), cerebro-spinal fluid (CSF), and white matter (WM) from the acquired images. After segmentation, the feature extraction was performed by utilizing dual tree complex wavelet transform (DTCWT), local ternary pattern (LTP) and Tamura features to extract the feature vectors from the segmented brain tissues. Then, ReliefF methodology was used to select the active features from the extracted feature vectors. Finally, the selected active feature values were classified into three classes [AD, normal and mild cognitive impairment (MCI)] utilizing deep neural network (DNN) classifier. From the simulation result, it is clear that the proposed framework achieved good performance in disease classification and almost showed 2.2–6% enhancement in accuracy of all four datasets. [ABSTRACT FROM AUTHOR]

Cocoa hybridisation generates new varieties which are resistant to several plant diseases, but has individual chemical characteristics that affect chocolate production. Image analysis is a useful method for visual discrimination of cocoa beans, while deep learning (DL) has emerged as the de facto technique for image processing. However, these algorithms require a large amount of data and careful tuning of hyperparameters. Since it is necessary to acquire a large number of images to encompass the wide range of agricultural products, in this paper, we compare a Deep Computer Vision System (DCVS) and a traditional Computer Vision System (CVS) to classify cocoa beans into different varieties. For DCVS, we used a Resnet18 and Resnet50 as backbone, while for CVS, we experimented traditional machine learning algorithms, Support Vector Machine (SVM), and Random Forest (RF). All the algorithms were selected since they provide good classification performance and their potential application for food classification A dataset with 1,239 samples was used to evaluate both systems. The best accuracy was 96.82% for DCVS (ResNet 18), compared to 85.71% obtained by the CVS using SVM. The essential handcrafted features were reported and discussed regarding their influence on cocoa bean classification. Class Activation Maps was applied to DCVS's predictions, providing a meaningful visualisation of the most important regions of the images in the model. [ABSTRACT FROM AUTHOR]

Image analysis can provide reproducible, objective and accurate results using a non-destructive, inexpensive procedure. The aim of this study was to evaluate the usefulness of the textures calculated from images of the flesh and skin of tomato fruit for cultivar discrimination. The color images of six tomato cultivars were acquired for whole peeled tomatoes and whole tomatoes with skin using a digital camera. The images were converted to color channels R, G, B, L, a, b, X, Y, and Z. The discriminative models were built based on a set of selected textures from all color channels, each color channel, and color space, separately. For images of tomato flesh and skin, the highest average accuracies equal to 92.67% and 94.33%, respectively, were obtained for models combining textures selected from all channels. For color spaces, the correctness reached 92% and 94% for tomato flesh and skin images, respectively. In the case of color channels, cultivar discrimination reached 86.33% for channel a for tomato flesh and 88.67% for channel b for tomato skin. The developed models can be used to evaluate the authenticity of tomato cultivars. [ABSTRACT FROM AUTHOR]

With the development of Computer-aided Diagnosis (CAD) and image scanning techniques, Whole-slide Image (WSI) scanners are widely used in the field of pathological diagnosis. Therefore, WSI analysis has become the key to modern digital histopathology. Since 2004, WSI has been used widely in CAD. Since machine vision methods are usually based on semi-automatic or fully automatic computer algorithms, they are highly efficient and labor-saving. The combination of WSI and CAD technologies for segmentation, classification, and detection helps histopathologists to obtain more stable and quantitative results with minimum labor costs and improved diagnosis objectivity. This paper reviews the methods of WSI analysis based on machine learning. Firstly, the development status of WSI and CAD methods are introduced. Secondly, we discuss publicly available WSI datasets and evaluation metrics for segmentation, classification, and detection tasks. Then, the latest development of machine learning techniques in WSI segmentation, classification, and detection are reviewed. Finally, the existing methods are studied, and the application prospects of the methods in this field are forecasted. [ABSTRACT FROM AUTHOR]

The orthogonal moments have recently achieved outstanding predictive performance and become an indispensable tool in a wide range of imaging and pattern recognition applications, including image reconstruction, image classification and object detection. We present in this paper, a new set of orthogonal functions, called "Orthogonal helmet functions." Using these functions we introduce three new sets of orthogonal moments and their invariants to scaling, rotation and translation for image representation and recognition, named, respectively, "the orthogonal helmet-Fourier moments" for the gray-level images, the multi-channel orthogonal helmet-Fourier moments and the quaternion orthogonal helmet-Fourier moments (QHFMs) for the color images. We introduce a series of experimental tests in image analysis and pattern recognition to validate the theoretical framework of our approach. The performance of these feature vectors is compared with the existing orthogonal invariant moments. The results of the comparative study show the efficiency and the superiority of our three orthogonal invariant moments. Thanks to our orthogonal moments QHFMs, we were able to lift the image recognition quality with rate can reach 2.06 %. [ABSTRACT FROM AUTHOR]

Ensemble learning has piqued the curiosity of the machine learning applications. It recently drawn serious attention in computer-aided diagnostic system (CADs) due to their potential to significantly increase the prediction performance, especially in mass classification in the mammogram. The ensemble pruning technique is used to reduce the ensemble size and improve its performance by selecting an optimal subset from a pool of individual classifiers. Among ensemble pruning techniques, the metaheuristic Bees algorithm (BA) showed reliable performance in terms of the selected ensemble's accuracy. However, BA's random initialization cannot guarantee whether the optimal ensemble will be selected, which leads to lesser classification results. Thus, this study introduces a selective Random Start Best step (RSB) initialization for BA to get an optimal ensemble pruning solution. Moreover, fusing ensemble members with equal weights will reduce the performance of the ensemble. To overcome this issue, a Local Weighted Majority Voting (L-WMV) is proposed beside the RSB. The proposed RSB(L-WMV) method for solving ensemble pruning and fussing issues was assessed on the mammogram image dataset that has been collected from Hospital Kuala Lumpur (HKL). Furthermore, the proposed RSB(L-WMV) was applied to the Mammographic Image Analysis Society (MIAS) benchmark dataset to show the proposed method's effectiveness. The obtained results using various evaluation metrics (accuracy, sensitivity, specificity, AUC) reveal the superiority of the proposed RSB(L-WMV) compared to similar methods in the literature. [ABSTRACT FROM AUTHOR]

Medical image analysis plays a very indispensable role in providing the best possible medical support to a patient. With the rapid advancements in modern medical systems, these digital images are growing exponentially and reside in discrete places. These images help a medical practitioner in understanding the problem and then the best suitable treatment. Radiological images are very often found to be the critical constituent of medical images. So, in health care, manual retrieval of visually similar images becomes a very tedious task. To address this issue, we have suggested a content-based medical image retrieval (CBMIR) system that effectively analyzes a Radiological image's primitive visual features. Since radiological images are in gray-scale form, these images contain rich texture and shape features only. So, we have suggested a novel multi-resolution radiological image retrieval system that uses texture and shape features for content analysis. Here, we have employed a multi-resolution modified block difference of inverse probability (BDIP) and block-level variance of local variance (BVLC) for shape and texture features, respectively. Our proposed scheme uses a multi-resolution and variable window size feature extraction strategy to maintain the block-level co-relation and extract more salient visual features. Further, we have used the MURA x-ray image dataset, which has 40561 images captured from 12173 different patients to demonstrate the proposed scheme's retrieval performance. We have also performed and compared image retrieval experiments on Brodatz and STex texture, Corel-1K, and GHIM-10K natural image datasets to demonstrate the robustness and improvement over other contemporaries. [ABSTRACT FROM AUTHOR]

The aim of the research was to compare the possibility of distinguishing the cultivars of processed beetroots using image analysis technique and sensory evaluation. The differentiation of processed samples was tested for freeze-dried beetroot 'Czerwona Kula' and 'Cylindra', lacto-fermented beetroot 'Czerwona Kula' and 'Cylindra', freeze-dried lacto-fermented beetroot 'Czerwona Kula' and 'Cylindra'. The textures from the images of quarters of root slices, as well as sensory attributes evaluated by expert sensory assessors, were determined. The differences in the means of selected textures from color spaces Lab, RGB and XYZ for different cultivars of raw and processed beetroots were observed. The raw beetroots 'Czerwona Kula' and 'Cylindra' were discriminated with the accuracy of up to 94.5% for models built based on selected texture from color space RGB. In the case of processed beetroots 'Czerwona Kula' and 'Cylindra', the accuracy reached 96% (color space Lab) for freeze-dried beetroots, 99% (color space Lab) for lacto-fermented beetroots, 98.5% (color space Lab) for freeze-dried lacto-fermented beetroots. In the case of sensory attributes, no statistically significant differences were observed between the beetroot samples. [ABSTRACT FROM AUTHOR]

The fast growth of using digital images in the virtual world and, The advance of image processing tools makes an image under the effect of attackers or intruders. Attackers tamper digital images and divert the content of the image from its true meaning. The manipulation in digital images makes tampering hard to detect with the naked eye. Therefore, image forensic analysis is developed to keep up and protect the authenticity and rights of the owner of digital images. The Copy-move forgery detection (CMFD) scheme is the popular type in image forensic analysis. This paper presents a merged CMFD scheme. This scheme contains a preparing process and three layers of processing. In the preparing process, Haar Discrete Wavelet Transform(HDWT) automates the number of segments before applying the segmentation process. The first layer, Simple Linear Iterative Clustering(SLIC)segmentation method is proposed to split images into irregular labels. Then, classification these segments into two main types called texture or smooth regions based on the Entropy metric. In the second layer, the keypoint-based technique is adopted. Speed Up Robust Feature(SURF) as detector and Histogram Of Oriented Gradient (HOG) as a descriptor is applied on each region. SURF-HOG to extract key points from regions with different Threshold values. In the third layer, an efficient probabilistic false positive removal filter(M-SAC) is employed. It aims to include the correct results and exclude false results from the output detected image. Subsequently, increase TPR and decrease FPR. The proposed scheme is evaluated by using(IMD and MICC-F220)data sets. The photometric attacks(brightness, blurring, JPEG compression) and geometric transformation attacks(scaling, rotation) are applied in these datasets. The experimental results indicate that the proposed scheme is fast, efficient, and high performance under simple and compound attacks. It has high TPR, Low FPR and, makes the scheme more dynamic and suitable in image forensic analysis. [ABSTRACT FROM AUTHOR]

Many computer vision-based techniques utilize semantic information i.e. scene text present in a natural scene for image analysis. Subsequently, in recent times researchers pay more attention to key tasks such as scene text detection, recognition, and end-to-end system. In this survey, we have given a comprehensive review of the recent advances on these key tasks. The review focused firstly on the traditional methods and their categorization, also show the evolution of scene text detection, recognition methods, and end-to-end systems with their pros and cons. Secondly, this survey focuses on the latest state-of-the-art (SOTA) methods based on transfer learning and additionally do the extension of scene text reading system i.e. salient text detection, text or non-text image classification, a fusion of scene text in vision and language, etc. After that, we have done a performance analysis on various SOTA methods on the various key issues and techniques. Finally, we discuss the various evaluation metrics and standard dataset on which the various SOTA methods of scene text detection is investigated and compared. [ABSTRACT FROM AUTHOR]

Owing to the sequential collection of phase encoded data in k-space, magnetic resonance (MR) imaging suffers from long acquisition time. One possible measure to reduce the long acquisition time is to reconstruct MR image using a subset of k-space MR data rather than the complete set. In this work, we propose to implement a K sparse autoencoder model for reconstruction of MR image from undersampled k-space data. Autoencoder models, which have shown great ability in capturing the complex features of input data, can be used to reconstruct high-quality MR image. The reconstruction process involved solving an optimization problem whose solution was expected to satisfy the data consistency and also lie in close proximity to the output space of trained K sparse autoencoder. Observing the effect of sparsity value enforced by K sparse autoencoder on the reconstructed output, we implemented the cascaded form of reconstruction, incorporating three K sparse autoencoders with three different K values. Using MR-PD and MR-T1 images, reconstruction performance of the proposed approach was compared with those of the conventional reconstruction approaches. The quantitative as well as the qualitative analysis of the reconstructed images, obtained using the proposed approach, validates the efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

Contrast enhancement is an important pre-processing task in any Image Analysis (IA) system. In this paper, we formulate the image contrast enhancement problem as an optimization problem where the goal is to optimize the pixel intensity values of an input image to obtain a contrast enhanced version of the same. This optimization task is executed by suitably customizing a nature-inspired optimization algorithm called Selfish Herd Optimizer (SHO). The optimization problem is solved using two different solution representations: pixel wise optimization (SHO(direct)) and transformation function based optimization (SHO(transformation)). Moreover, an ablation study is performed to select the most appropriate parameters which can be used in fitness measure for this optimization problem. On experimenting over the popular Kodak image dataset, it has been observed that the proposed methods outperform many existing methods published recently. Further comparisons indicate that the direct approach performs better than its transformation counterpart. This paper further investigates the robustness of SHO(direct) approach by applying it to enhance the degraded document images of H-DIBCO 2018. [ABSTRACT FROM AUTHOR]

The presented method allows measuring the braid angle, taking into account the magnitude of its deviation from the specified value, which makes it possible to assess the braid angle unevenness in the structure of the textile preform. The method was developed using image analysis tools and fast Fourier transform, the mathematical apparatus of which allow investigating the frequency characteristics of digital images of braided structures and measuring the yarns and threads orientation in a braided structure, taking into account their unevenness. The accuracy of calculations has been confirmed by the results of the analysis of images of braided structures with specified parameters, for which the braid angle and the magnitude of its deviation from the specified value have been measured. A conclusion about the efficiency of using the developed method for accurate measurement of the braid angle and the magnitude of its deviation from the specified value in braided preforms has been made. [ABSTRACT FROM AUTHOR]

This study aimed to determine the discriminatory power of textural features to differentiate the sorghum grains subjected to normal, mild deficit, and severe deficit irrigation. The studies were carried out with the use of image processing, discrimination analysis, analysis of variance and cluster analysis using the selected texture parameters calculate for images from individual color channels L, a, b, R, G, B, U, V, S, X, Y and Z. The results indicated that different levels of irrigation can discriminate the sorghum grain with an accuracy of up to about 100%. Most of the genotypes for each level of irrigation were different in the terms of values of textural features and formed separate homogeneous groups. Drought is one of the limiting factors contributing to a decrease in sorghum grain productivity and nutritional quality, especially when it is cultivated in a marginal area. Therefore, low-quality grains produced under water stress should be recognized before they enter into the food and feed chain. The application of image analysis based on textures of sorghum grain images proved to be useful for the discrimination of sorghum grains subjected to drought stress. The applied procedure provided the fast, objective results that may be applied in practice for screening distinguishing the sorghum grains with different irrigation levels. [ABSTRACT FROM AUTHOR]