Search

Abstract: This study focused on finding the potential of image texture analysis for determining the spatiotemporal fracture behavior of crispy or crunchy food products. Two-dimensional stress distribution maps were obtained during compression failure of six dry-crisp samples at four loading stages. Applying gray-level co-occurrence matrix statistics to the stress distribution maps, four major textural features were extracted, which represent the spatial pattern of the stress intensity. Stress distribution maps for the samples were classified into original classes depending on their image textural features, using a canonical discriminant analysis with an accuracy of 99%. Local variations in stress intensity and the existence of areas with the same stress intensity at higher loading stages were critical spatial factors in discriminating among the different samples. In addition to spatial factors, temporal changes in image textural features during loading also provided information necessary for sample identification. This application of image texture analysis to stress distribution maps reveals the characteristics of spatiotemporal stress distribution accompanying the dynamic fracture process for crispy or crunchy samples. [Copyright &y& Elsevier]

Abstract: The objective of this work was to assess the crumb grain appearance of bread loaves prepared with four organic flours (11.3–12.4% protein content) in comparison with a control bread prepared with non-organic flour (12.4% protein content), by means of three statistical and one spectral grey-level image texture analysis methods. Stepwise-selected textural features independently extracted from each method could successfully distinguish 94–97% of the non-organic bread’s crumb grain images, and could classify 76–83% of the organic bread’s crumb grain images into their respective flour types using cross-validation. The statistical texture analysis methods (explained variance 91–96%) depicted the bread crumb visual texture better than the spectral method (explained variance 80%). Factor analysis performed over the highest discriminant textural features identified three major components: grain coarseness, heterogeneity and isotropy, being the last component extracted only from the spectral method. This model showed that crumb grain of organic breads was variably heterogeneous, coarse and, in some cases, with a high degree of isotropy, since their cells were much more rounded than the non-organic bread’s crumb cells. [Copyright &y& Elsevier]

Surface texture is an important quality characteristic of many products. This paper provides an overview of several different approaches to image texture analysis and demonstrates their use on the problem of classifying a set of rolled steel sheets into various quality grades. Methods covered include traditional statistical approaches such as gray level co-occurrence matrix (GLCM) methods, multivariate statistical approaches based on PCA and PLS, and wavelet texture analysis.Traditional multivariate classification approaches, such as PLS-DA, applied directly to the images are shown to fail because of the loss of spatial identity of the variables (pixels) in those approaches, and the lack of congruency of the images. However, approaches that re-introduce spatial information, such as performing two-dimensional FFT on the images prior to applying multivariate methods can perform well. A new approach that re-introduces spatial information through image shifting and stacking, followed by multivariate image analysis (MIA) is presented and shown to work well. It can also be used to develop optimal spatial filters for extracting texture information. Wavelet texture analysis (WTA) methods are discussed and insight into their space/frequency decomposition behavior is used to show why they are generally considered to be state of the art in texture analysis. [Copyright &y& Elsevier]

• 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]

Addressing global declines in biodiversity requires accurate assessments of key environmental attributes determining patterns of species diversity. Spatial heterogeneity of vegetation strongly affects species diversity patterns, and measures of vegetation structure derived from lidar and satellite image texture analysis correlate well with species richness. Our goal here was to gain a better understanding of why image texture explains bird richness, by linking field-based measures of vegetation structure directly with both image texture and bird richness. In addition, we asked how image texture compares with lidar-based canopy height variability, and how sensor resolution affects the explanatory power of image texture. We generated texture metrics from 30 m (Landsat 8) and 10 m (Sentinel-2) resolution Enhanced Vegetation Index (EVI) imagery from 2017 to 2019. We compared textures with vegetation metrics and bird richness data from 27 National Ecological Observatory Network (NEON) terrestrial field sites across the continental US. Both 30 and 10 m resolution texture metrics were strongly correlated with lidar-based canopy height variability (|r| = 0.64 and 0.80, respectively). Texture was moderately correlated with field-based metrics, including variability of vegetation height and tree stem diameter, and foliage height diversity (range |r| = 0.31–0.52). Generally, 10 m resolution texture had stronger correlations with lidar and field-based metrics than 30 m resolution texture. In univariate linear models of total bird richness, 10 m resolution texture metrics also had higher explanatory power (up to R 2 adj = 0.45), than 30 m texture metrics (up to R 2 adj = 0.31). Among all metrics evaluated, the 10 m homogeneity texture was the best univariate predictor of total bird richness. In multivariate bird richness models that combined texture with lidar-based canopy height variability and field-based metrics, both 30 m and 10 m resolution texture metrics were selected in top-ranked models and independently contributed explanatory power (up to R 2 adj = 46%). Lidar-based canopy height variability was also selected in a top-ranked model of total bird richness, but independently contributed only 15% of the variance explained. Our results show satellite image texture characterized multiple features of structural and compositional vegetation heterogeneity, complemented more commonly used metrics in models of bird richness and for some guilds outperformed both lidar-based canopy height variability and field-based vegetation measurements. Ours is the first study to directly link image texture both to specific components of vegetation heterogeneity and to bird richness across multiple ecoregions and spatial resolutions, thereby shedding light on habitat features underlying the strong correlation between image texture and biodiversity. • Image texture captures heterogeneity in both vegetation structure and composition. • 10 m resolution texture outperforms 30 m texture in bird richness models. • Texture metrics outperform lidar canopy height variability in bird richness models. • Image texture has exciting potential for biodiversity research and conservation. [ABSTRACT FROM AUTHOR]

When designing artificial vision systems, it may be useful to examine the solutions 0.5 billion years of biological evolution have produced. Recent studies of human vision; studies of macaque visual cortical function; and behavioural studies of bee vision, all indicate that different species have evolved related approaches for discriminating image textures. This common strategy uses short-range 4th-order spatial correlations. Isotrigon textures, ensemble averages of which have 3rd-order correlation functions that are equal to 0, are useful for studying this sense. Recent results from humans and bees, and methods for producing new isotrigon textures are described. [Copyright &y& Elsevier]

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]

• We propose a rain streaks removal method in single image based on texture constraint of background scene, which is established by explicitly utilizing the frequency, direction characteristic of rain streaks, and the non-rain texture clues learned from natural images. • Different from adopting an online learning program to provide constraints, we propose a ICA-based fusion method. The ICA allows to learn once for further use, without the need to learn for each rain image. It reduces the computation time. • A new decomposition model is proposed, where a texture constraint for background scene and a low-rank appearance constraint for rain streaks are both utilized to reduce the confusion between image texture and rain structure. Removing rain streaks from single image is mathematically ill-defined and the known strategies tend to over-smooth the background and remove image details. To tackle this problem, this paper proposes a novel two-stage system. Firstly, in view of the frequency and direction of rain streaks, Gabor filter is first used to suppress rain streaks. Based on the bases extracted from natural images, several Gabor filtered images extracted from the input rain image are fused by a new proposed method, and the fused result provides a texture constraint for the non-rain part. Secondly, a low-rank model is adopted to describe rain streaks as they take on similar and repeated patterns in an imaging scene. By combining the texture constraint and the low-rank model, a global cost function is constructed. Finally, an optimization strategy is proposed based on the split Bregman technique, which solves the function with high performance. A large number of experimental results show the competitive performance and efficiency of the proposed method in comparison with the state-of-the-art methods, making it more applicable in real practices. [ABSTRACT FROM AUTHOR]

Abstract: Product quality monitoring by image texture analysis underwent a tremendous growth in the last few years in several industrial sectors, due to the availability of low-cost digital imaging sensors. Multivariate image analysis (MIA) can be used within an image texture analysis technique to provide a spatial statistical characterization of an image. However, in most cases this spatial characterization is possible only for very local texture neighborhoods, due to the high computational cost of MIA. In this paper, the iMIA (improved Multivariate Image Analysis) algorithm is proposed, that improves over previous implementations of MIA by extending its range of applicability due to its reduced computational complexity and memory requirements. The proposed algorithm uses the Fourier transform and the convolution theorem to efficiently compute the MIA model, in such a way that the image texture can be characterized by taking into account also large neighborhood sizes. The proposed approach is applied to two case studies concerning the estimation of the fiber diameter distribution in nanostructured membranes, and the classification of paper surfaces. The results suggest that the optimum range of spatial statistics used for characterizing the image is related to the size of the main textural features. [Copyright &y& Elsevier]

Creep deformation of human vertebrae accumulates under physiological levels of load and is understood to contribute to the progression toward clinically observable vertebral fracture. However, little information is available in terms of clinically measurable predictors of creep behavior in human vertebrae. In this study, creep tests were performed on 22 human cadaveric T12 vertebrae (13 male, 9 female; age 41–90). Areal and volumetric bone density parameters were measured from the same specimens using dual x-ray absorptiometry and high resolution computed tomography. Image textural analyses (which probe the organization of image intensities within the cancellous bone in low resolution clinical imaging) were performed using digital tomosynthesis (DTS) images. Multiple regression models were constructed to examine the relationship between creep properties and bone density and DTS image textural parameters. For the standard clinical imaging configuration, models including DTS derived image textural parameters alone were generally more explanatory (adjusted R2: 0.14–0.68) than those with bone density parameters forced in the models (adjusted R2: 0.17–0.61). Metrics of textural heterogeneity and anisotropy presented as the most explanatory imaging markers for creep deformation and recovery from creep. These metrics of image texture may help provide, independent from bone mass, important clinically measurable indicators of the time dependent deformation of human vertebrae. [ABSTRACT FROM AUTHOR]

Abstract: Quasi-supervised learning is a statistical learning algorithm that contrasts two datasets by computing estimate for the posterior probability of each sample in either dataset. This method has not been applied to histopathological images before. The purpose of this study is to evaluate the performance of the method to identify colorectal tissues with or without adenocarcinoma. Light microscopic digital images from histopathological sections were obtained from 30 colorectal radical surgery materials including adenocarcinoma and non-neoplastic regions. The texture features were extracted by using local histograms and co-occurrence matrices. The quasi-supervised learning algorithm operates on two datasets, one containing samples of normal tissues labelled only indirectly, and the other containing an unlabeled collection of samples of both normal and cancer tissues. As such, the algorithm eliminates the need for manually labelled samples of normal and cancer tissues for conventional supervised learning and significantly reduces the expert intervention. Several texture feature vector datasets corresponding to different extraction parameters were tested within the proposed framework. The Independent Component Analysis dimensionality reduction approach was also identified as the one improving the labelling performance evaluated in this series. In this series, the proposed method was applied to the dataset of 22,080 vectors with reduced dimensionality 119 from 132. Regions containing cancer tissue could be identified accurately having false and true positive rates up to 19% and 88% respectively without using manually labelled ground-truth datasets in a quasi-supervised strategy. The resulting labelling performances were compared to that of a conventional powerful supervised classifier using manually labelled ground-truth data. The supervised classifier results were calculated as 3.5% and 95% for the same case. The results in this series in comparison with the benchmark classifier, suggest that quasi-supervised image texture labelling may be a useful method in the analysis and classification of pathological slides but further study is required to improve the results. [Copyright &y& Elsevier]

Abstract: Counting craters is a paramount tool of planetary analysis because it provides relative dating of planetary surfaces. Dating surfaces with high spatial resolution requires counting a very large number of small, sub-kilometer size craters. Exhaustive manual surveys of such craters over extensive regions are impractical, sparking interest in designing crater detection algorithms (CDAs). As a part of our effort to design a CDA, which is robust and practical for planetary research analysis, we propose a crater detection approach that utilizes both shape and texture features to identify efficiently sub-kilometer craters in high resolution panchromatic images. First, a mathematical morphology-based shape analysis is used to identify regions in an image that may contain craters; only those regions – crater candidates – are the subject of further processing. Second, image texture features in combination with the boosting ensemble supervised learning algorithm are used to accurately classify previously identified candidates into craters and non-craters. The design of the proposed CDA is described and its performance is evaluated using a high resolution image of Mars for which sub-kilometer craters have been manually identified. The overall detection rate of the proposed CDA is 81%, the branching factor is 0.14, and the overall quality factor is 72%. This performance is a significant improvement over the previous CDA based exclusively on the shape features. The combination of performance level and computational efficiency offered by this CDA makes it attractive for practical application. [Copyright &y& Elsevier]

Abstract: Many recent studies on ultrasonic particle image velocimetry (Echo PIV) showed that the accuracy of two-dimensional (2-D) flow velocity measured depends largely on the concentration of ultrasound contrast agents (UCAs) during imaging. This article presents a texture-based method for identifying the optimum microbubble concentration for Echo PIV measurements in real-time. The texture features, standard deviation of gray level, and contrast, energy and homogeneity of gray level co-occurrence matrix were extracted from ultrasound contrast images of rotational and pulsatile flow (10 MHz) in vitro and in vivo mouse common carotid arterial flow (40 MHz) with UCAs at various concentrations. The results showed that, at concentration of 0.8∼2 × 103 bubbles/mL in vitro and 1∼5 × 105 bubbles/mL in vivo, image texture features had a peak value or trough value, and velocity vectors with high accuracy can be obtained. Otherwise, poor quality velocity vectors were obtained. When the texture features were used as a feature set, the accuracy of K-nearest neighbor classifier can reach 86.4% in vitro and 87.5% in vivo, respectively. The texture-based method is shown to be able to quickly identify the optimum microbubble concentration and improve the accuracy for Echo PIV imaging. [Copyright &y& Elsevier]

Abstract: The spatial variability of remotely sensed image values provides important information about the arrangement of objects and their spatial relationships within the image. The characterisation of spatial variability in such images, for example, to measure of texture, is of great utility for the discrimination of land cover classes. To this end, the variogram, a function commonly applied in geostatistics, has been used widely to extract image texture for remotely sensed data classification. The aim of this study was to assess the increase in accuracy that can be achieved by incorporating univariate and multivariate textural measures of Landsat TM imagery in classification models applied to large heterogeneous landscapes. Such landscapes which difficult to classify due to the large number of land cover categories and low inter-class separability. Madogram, rodogram and direct variogram for the univariate case, and cross- and pseudocross variograms for the multivariate one, together with multi-seasonal spectral information were used in a Random Forest classifier to map land cover types. The addition of spatial variability into multi-seasonal Random Forest models leads to an increase in the overall accuracy of 8%, and to an increase in the Kappa index of 9%, respectively. The increase in per categories Kappa for the textural Random Forest model reached 30% for certain categories. This study demonstrates that the use of information on spatial variability produces a fundamental increase in per class classification accuracy of complex land-cover categories. [Copyright &y& Elsevier]

Abstract: Estimation of the orientation of a textured planar surface is one of the basic tasks in the area of “shape from texture”. For the solution of this task, many successful approaches were proposed. In this paper, we have examined a few unaddressed questions: First, is there a mathematical formulation that relates the spectral characteristics of the texture pattern and the orientation of an inclined planar surface in a polar-coordinate system? Second, is there a good wavelet-based approach that produces an accurate estimate of the orientation angle of the textured planar surface by analyzing the spectral behavior of one single uncalibrated image? To answer these questions at first we present the formulation of a “texture projective equation”, which relates the depth and orientation of an inclined planar surface in a polar coordinate system with the spectral properties of its image texture. A suitable imaging geometry has been considered to enable separable analysis of the effect of inclination of the texture surface. Next, a method for shape from texture is presented based on discrete wavelet analysis to estimate the orientation of the planar surface. This approach although designed mainly for M-channel wavelets, is also applicable for dyadic wavelet analysis. Texture characteristics in the subbands of wavelet decomposition are analyzed using scalograms, and quantitatively evaluated based on texture projective equations. The proposed method of estimation of the orientation of a planar texture surface is evaluated using a set of simulated and real world textured images. [Copyright &y& Elsevier]

Image texture description and analysis technology are the basis of many practical applications in pattern recognition. This paper presents a novel and simple, yet powerful method, namely multiple channels local binary pattern (MCLBP), which is the natural extension and development of local binary pattern (LBP) algorithm for color texture representation and classification. MCLBP combines single-channel texture characteristics with multi-channel color information, which reflects the correlations and dependency among different channels. Furthermore, we decompose local color differences into color-difference signs and color-difference magnitudes and MCLBP is extended to MCLBP+M. Then, the resulted image descriptor is a histogram representation, which fuses rich features including color difference sign and color difference magnitude. Comprehensive experiments conducted on five benchmark databases, including Outex, KTH-TIPS, CUReT, STex and KTH-TIPS2-b clearly demonstrate that our proposed method outperforms most of the existed color texture features in terms of classification accuracy. Particularly, our method achieves the best classification performance in CUReT and STex databases. • A multi-channels LBP encodes inner- and inter-channel features of color images. • MCLBP extracts local features from three channels at once. • MCLBP+M characterizes both color difference signs and color difference magnitudes. • Comprehensive experiments are conducted on five benchmark datasets. [ABSTRACT FROM AUTHOR]

Multi-focus image fusion is an effective method of information fusion that can take a series of source images and obtain a fused image where everything is in focus. In this paper, a multi-focus image fusion method based on image texture that adopts a modified Pulse-Coupled Neural Network (PCNN) approach is proposed. First, the texture of an image is obtained by means of image cartoon and texture decomposition. An ignition image is then acquired by inputting the image textures into a modified PCNN. Ignition images are compared to each other to obtain an initial decision map. A small object detection and bilateral filter is then applied to the initial decision map to reduce noise and enable smoother processing. Finally, the source images and decision map are used to produce the fused image. Experimental results demonstrate that the proposed method effectively preserves the source images information while delivering good image fusion performance. • An image fusion method based on image decomposition and PCNN is proposed. • A modified PCNN model is proposed that is more applicable to multi-focus image processing. • Our Method can fuse the color image and gray image. • Experiments result shows our method has a good performance. [ABSTRACT FROM AUTHOR]