Texture analysis Anno 1983

Perceptual Texture Similarity Estimation: An Evaluation of Computational Features

Estimation of texture similarity is fundamental to many material recognition tasks. This study uses fine-grained human perceptual similarity ground-truth to provide a comprehensive evaluation of 51 texture feature sets. We conduct two types of evaluation and both show that these features do not estimate similarity well when compared against human agreement rates, but that performances are improved when the features are combined using a Random Forest. Using a simple two-stage statistical model we show that few of the features capture long-range aperiodic relationships. We perform two psychophysical experiments which indicate that long-range interactions do provide humans with important cues for estimating texture similarity. This motivates an extension of the study to include Convolutional Neural Networks (CNNs) as they enable arbitrary features of large spatial extent to be learnt. Our conclusions derived from the use of two pre-trained CNNs are: that the large spatial extent exploited by the networks' top convolutional and first fully-connected layers, together with the use of large numbers of filters, confers significant advantage for estimation of perceptual texture similarity.

Learning-based defect recognition for quasi-periodic HRSTEM images

Controlling crystalline material defects is crucial, as they affect properties of the material that may be detrimental or beneficial for the final performance of a device. Defect analysis on the sub-nanometer scale is enabled by high-resolution scanning transmission electron microscopy (HRSTEM), where the identification of defects is currently carried out based on human expertise. However, the process is tedious, highly time consuming and, in some cases, yields ambiguous results. Here we propose a semi-supervised machine learning method that assists in the detection of lattice defects from atomic resolution HRSTEM images. It involves a convolutional neural network that classifies image patches as defective or non-defective, a graph-based heuristic that chooses one non-defective patch as a model, and finally an automatically generated convolutional filter bank, which highlights symmetry breaking such as stacking faults, twin defects and grain boundaries. Additionally, we suggest a variance filter to segment amorphous regions and beam defects. The algorithm is tested on III-V/Si crystalline materials and successfully evaluated against different metrics and a baseline approach, showing promising results even for extremely small training data sets and for noise compromised images. By combining the data-driven classification generality, robustness and speed of deep learning with the effectiveness of image filters in segmenting faulty symmetry arrangements, we provide a valuable open-source tool to the microscopist community that can streamline future HRSTEM analyses of crystalline materials.

Visual Functions of Primate Area V4

Area V4-the focus of this review-is a mid-level processing stage along the ventral visual pathway of the macaque monkey. V4 is extensively interconnected with other visual cortical areas along the ventral and dorsal visual streams, with frontal cortical areas, and with several subcortical structures. Thus, it is well poised to play a broad and integrative role in visual perception and recognition-the functional domain of the ventral pathway. Neurophysiological studies in monkeys engaged in passive fixation and behavioral tasks suggest that V4 responses are dictated by tuning in a high-dimensional stimulus space defined by form, texture, color, depth, and other attributes of visual stimuli. This high-dimensional tuning may underlie the development of object-based representations in the visual cortex that are critical for tracking, recognizing, and interacting with objects. Neurophysiological and lesion studies also suggest that V4 responses are important for guiding perceptual decisions and higher-order behavior.

A Novel Texture-Quantization-Based Reversible Multiple Watermarking Scheme Applied to Health Information System

The recent innovations in information and communication technologies have appreciably changed the panorama of health information system (HIS). These advances provide new means to process, handle, and share medical images and also augment the medical image security issues in terms of confidentiality, reliability, and integrity. Digital watermarking has emerged as new era that offers acceptable solutions to the security issues in HIS. Texture is a significant feature to detect the embedding sites in an image, which further leads to substantial improvement in the robustness. However, considering the perspective of digital watermarking, this feature has received meager attention in the reported literature. This paper exploits the texture property of an image and presents a novel hybrid texture-quantization-based approach for reversible multiple watermarking. The watermarked image quality has been accessed by peak signal to noise ratio (PSNR), structural similarity measure (SSIM), and universal image quality index (UIQI), and the obtained results are superior to the state-of-the-art methods. The algorithm has been evaluated on a variety of medical imaging modalities (CT, MRA, MRI, US) and robustness has been verified, considering various image processing attacks including JPEG compression. The proposed scheme offers additional security using repetitive embedding of BCH encoded watermarks and ADM encrypted ECG signal. Experimental results achieved a maximum of 22,616 bits hiding capacity with PSNR of 53.64 dB.

WEAR PARTICLE TEXTURE CLASSIFICATION USING ARTIFICIAL NEURAL NETWORKS

Analysis of wear debris carried by a lubricant in an oil-wetted system provides important information about the condition of a machine. This paper describes the analysis of microscopic metal particles generated by wear using computer vision and image processing. The aim is to classify these particles according to their morphology and surface texture and by using the information obtained, to predict wear failure modes in engines and other machinery. This approach obviates the need for specialists and reliance on human visual inspection techniques. The procedure reported in this paper, is used to classify surface features of the wear particles by using artificial neural networks. A visual comparison between cooccurrence matrices representing five different texture classes is described. Based on these comparisons, matrices of reduced sizes are utilized to train a feed-forward neural classifier in order to distinguish between the various texture classes.

GENETIC ALGORITHM OPTIMIZATION OF ADAPTIVE MULTI-SCALE GLCM FEATURES

We introduce a new second-order method of texture analysis called Adaptive Multi-Scale Grey Level Co-occurrence Matrix (AMSGLCM), based on the well-known Grey Level Co-occurrence Matrix (GLCM) method. The method deviates significantly from GLCM in that features are extracted, not via a fixed 2D weighting function of co-occurrence matrix elements, but by a variable summation of matrix elements in 3D localized neighborhoods. We subsequently present a new methodology for extracting optimized, highly discriminant features from these localized areas using adaptive Gaussian weighting functions. Genetic Algorithm (GA) optimization is used to produce a set of features whose classification "worth" is evaluated by discriminatory power and feature correlation considerations. We critically appraised the performance of our method and GLCM in pairwise classification of images from visually similar texture classes, captured from Markov Random Field (MRF) synthesized, natural, and biological origins. In these cross-validated classification trials, our method demonstrated significant benefits over GLCM, including increased feature discriminatory power, automatic feature adaptability, and significantly improved classification performance.

Computational perceptual features for texture representation and retrieval

A perception-based approach to content-based image representation and retrieval is proposed in this paper. We consider textured images and propose to model their textural content by a set of features having a perceptual meaning and their application to content-based image retrieval. We present a new method to estimate a set of perceptual textural features, namely coarseness, directionality, contrast, and busyness. The proposed computational measures can be based upon two representations: the original images representation and the autocorrelation function (associated with original images) representation. The set of computational measures proposed is applied to content-based image retrieval on a large image data set, the well-known Brodatz database. Experimental results and benchmarking show interesting performance of our approach. First, the correspondence of the proposed computational measures to human judgments is shown using a psychometric method based upon the Spearman rank-correlation coefficient. Second, the application of the proposed computational measures in texture retrieval shows interesting results, especially when using results fusion returned by each of the two representations. Comparison is also given with related works and show excellent performance of our approach compared to related approaches on both sides: correspondence of the proposed computational measures with human judgments as well as the retrieval effectiveness.

Analysis of multiple orientations

Estimation of local orientations in multivariate signals is an important problem in image processing and computer vision. This general problem formulation also covers optical flow estimation, which can be regarded as orientation estimation in space-time-volumes. Modelling a signal using only a single orientation, however, is often too restrictive, since occlusions and transparencies occur frequently, thus necessitating the modelling and analysis of multiple orientations. We, therefore, develop a unifying mathematical model for multiple orientations: Beyond describing an arbitrary number of orientations in scalar- and vector-valued image data such as color image sequences, it allows the unified treatment of additively and occludingly superimposed oriented structures as well as of combinations of these. Based on this model, we describe estimation schemes for an arbitrary number of additively or occludingly superimposed orientations in images. We confirm the performance of our framework on both synthetic and real image data.

Texture analysis in non-contrast enhanced CT: impact of malignancy on texture in apparently disease-free areas of the liver

OBJECTIVES

To determine whether texture analysis of non-contrast enhanced computed tomography (CT) images in apparently disease-free areas of the liver is altered by the presence of extra- and intra-hepatic malignancy in colorectal cancer patients.

MATERIALS AND METHODS

Hepatic attenuation and texture were assessed from non-contrast enhanced CT in three groups of colorectal cancer patients: (A) 15 controls with no malignancy; (B) nine patients with extra-hepatic malignancy but no liver involvement; (C) eight patients with hepatic metastases. Regions of interest were manually constructed only over apparently normal areas of liver tissue excluding major blood vessels and areas of intra-hepatic fat, which may otherwise alter CT texture irrespective of the presence of malignancy. Texture was analysed on unfiltered images and following band-pass image filtration to highlight image features at different spatial frequencies (fine: 2 pixels/1.68 mm in width, medium: 6 pixels/5.04 mm and coarse: 12 pixels/10.08 mm). The relative contributions made to the image by features at two different spatial frequencies were expressed as filter ratios (fine/medium, fine/coarse and medium/coarse). Texture was quantified as mean grey-level intensity, entropy and uniformity.

RESULTS

Texture was not altered on unfiltered images whereas relative texture analysis following image filtration identified differences in fine to medium texture ratios in apparently disease-free areas of the liver in patients with hepatic metastases as compared to patients with no tumour (entropy, p=0.0257) and patients with extra-hepatic disease (uniformity, p=0.0143).

CONCLUSIONS

Relative texture analysis of unenhanced hepatic CT can reveal changes in apparently disease-free areas of the liver that have previously required more complex perfusion measurements for detection.

Texture analysis of brain MRI evidences the amygdala activation by nociceptive stimuli under deep anesthesia in the propofol–formalin rat model

Magnetic resonance images of rat brain were analyzed by texture analysis in order to study the effects of a nociceptive stimulation (formalin test) under propofol deep anesthesia. Changes of the texture in different cerebral brain areas acquired before and after stimulation were checked. Our statistical analysis of texture shows that these changes were present only in the amygdala, in agreement with the facts already known about the unconscious memorization of nociceptive stimuli.

RR, Trad CS. Caracterização de lesões intersticiais de pulmão em radiograma de tórax utilizando análise local de textura

OBJETIVO: Caracterizar lesões intersticiais em radiografias frontais de tórax, com base na análise de atributos estatísticos de textura, os quais permitem detectar sinais de anormalidades com natureza difusa. MATERIAIS E MÉTODOS: O esquema começa com a segmentação semi-automática dos campos pulmonares, sendo o contorno externo marcado manualmente, com posterior divisão automática de cada pulmão em seis regiões. O banco de imagens utilizado neste trabalho é composto por 482 regiões obtidas de exames contendo lesões e 324 regiões obtidas de exames normais. Os atributos de textura são extraídos automaticamente de cada uma dessas regiões e uma seleção das melhores combinações de atributos é feita através da distância Jeffries-Matusita. A classificação das regiões em normal ou suspeita é feita pela comparação com os k vizinhos mais próximos e o treinamento do classificador é baseado na técnica de treino e teste "half-half" e correlação cruzada. RESULTADOS: Os resultados obtidos foram analisados através do valor da área sob a curva ROC ("receiver operating characteristic"), a qual indica um sistema perfeito para uma área igual a 1. Os resultados forneceram uma área sob a curva ROC (A Z) igual a 0,887, com valores de sensibilidade igual a 0,804 e especificidade igual a 0,793. CONCLUSÃO: Os resultados indicam que o sistema de caracterização baseado em atributos de textura possui bom potencial para o auxílio ao diagnóstico de lesões intersticiais de pulmão.

Automatic detection of abnormalities in chest radiographs using local texture analysis

A fully automatic method is presented to detect abnormalities in frontal chest radiographs which are aggregated into an overall abnormality score. The method is aimed at finding abnormal signs of a diffuse textural nature, such as they are encountered in mass chest screening against tuberculosis (TB). The scheme starts with automatic segmentation of the lung fields, using active shape models. The segmentation is used to subdivide the lung fields into overlapping regions of various sizes. Texture features are extracted from each region, using the moments of responses to a multiscale filter bank. Additional "difference features" are obtained by subtracting feature vectors from corresponding regions in the left and right lung fields. A separate training set is constructed for each region. All regions are classified by voting among the k nearest neighbors, with leave-one-out. Next, the classification results of each region are combined, using a weighted multiplier in which regions with higher classification reliability weigh more heavily. This produces an abnormality score for each image. The method is evaluated on two databases. The first database was collected from a TB mass chest screening program, from which 147 images with textural abnormalities and 241 normal images were selected. Although this database contains many subtle abnormalities, the classification has a sensitivity of 0.86 at a specificity of 0.50 and an area under the receiver operating characteristic (ROC) curve of 0.820. The second database consist of 100 normal images and 100 abnormal images with interstitial disease. For this database, the results were a sensitivity of 0.97 at a specificity of 0.90 and an area under the ROC curve of 0.986.

Three-dimensional texture analysis of MRI brain datasets

A method is proposed for three-dimensional (3-D) texture analysis of magnetic resonance imaging brain datasets. It is based on extended, multisort co-occurrence matrices that employ intensity, gradient and anisotropy image features in a uniform way. Basic properties of matrices as well as their sensitivity and dependence on spatial image scaling are evaluated. The ability of the suggested 3-D texture descriptors is demonstrated on nontrivial classification tasks for pathologic findings in brain datasets.

A new approach for subset 2-D AR model identification for describing textures

This paper addresses the problem of identification of appropriate autoregressive (AR) components to describe textural regions of digital images by a general class of two-dimensional (2-D) AR models. In analogy with univariate time series, the proposed technique first selects a neighborhood set of 2-D lag variables corresponding to the significant multiple partial auto-correlation coefficients. A matrix is then suitably formed from these 2-D lag variables. Using singular value decomposition (SVD) and orthonormal with column pivoting factorization (QRcp) techniques, the prime information of this matrix corresponding to different pseudoranks is obtained. Schwarz's (1978) information criterion (SIG) is then used to obtain the optimum set of 2-D lag variables, which are the appropriate autoregressive components of the model for a given textural image. A four-class texture classification scheme is illustrated with such models and a comparison of the technique with the work of Chellappa and Chatterjee (1985) is provided.

Methods in quantitative image analysis

The main steps of image analysis are image capturing, image storage (compression), correcting imaging defects (e.g. non-uniform illumination, electronic-noise, glare effect), image enhancement, segmentation of objects in the image and image measurements. Digitisation is made by a camera. The most modern types include a frame-grabber, converting the analog-to-digital signal into digital (numerical) information. The numerical information consists of the grey values describing the brightness of every point within the image, named a pixel. The information is stored in bits. Eight bits are summarised in one byte. Therefore, grey values can have a value between 0 and 256 (2(8)). The human eye seems to be quite content with a display of 5-bit images (corresponding to 64 different grey values). In a digitised image, the pixel grey values can vary within regions that are uniform in the original scene: the image is noisy. The noise is mainly manifested in the background of the image. For an optimal discrimination between different objects or features in an image, uniformity of illumination in the whole image is required. These defects can be minimised by shading correction [subtraction of a background (white) image from the original image, pixel per pixel, or division of the original image by the background image]. The brightness of an image represented by its grey values can be analysed for every single pixel or for a group of pixels. The most frequently used pixel-based image descriptors are optical density, integrated optical density, the histogram of the grey values, mean grey value and entropy. The distribution of the grey values existing within an image is one of the most important characteristics of the image. However, the histogram gives no information about the texture of the image. The simplest way to improve the contrast of an image is to expand the brightness scale by spreading the histogram out to the full available range. Rules for transforming the grey value histogram of an existing image (input image) into a new grey value histogram (output image) are most quickly handled by a look-up table (LUT). The histogram of an image can be influenced by gain, offset and gamma of the camera. Gain defines the voltage range, offset defines the reference voltage and gamma the slope of the regression line between the light intensity and the voltage of the camera. A very important descriptor of neighbourhood relations in an image is the co-occurrence matrix. The distance between the pixels (original pixel and its neighbouring pixel) can influence the various parameters calculated from the co-occurrence matrix. The main goals of image enhancement are elimination of surface roughness in an image (smoothing), correction of defects (e.g. noise), extraction of edges, identification of points, strengthening texture elements and improving contrast. In enhancement, two types of operations can be distinguished: pixel-based (point operations) and neighbourhood-based (matrix operations). The most important pixel-based operations are linear stretching of grey values, application of pre-stored LUTs and histogram equalisation. The neighbourhood-based operations work with so-called filters. These are organising elements with an original or initial point in their centre. Filters can be used to accentuate or to suppress specific structures within the image. Filters can work either in the spatial or in the frequency domain. The method used for analysing alterations of grey value intensities in the frequency domain is the Hartley transform. Filter operations in the spatial domain can be based on averaging or ranking the grey values occurring in the organising element. The most important filters, which are usually applied, are the Gaussian filter and the Laplace filter (both averaging filters), and the median filter, the top hat filter and the range operator (all ranking filters). Segmentation of objects is traditionally based on threshold grey values. (AB

A dual approach to structural texture analysis in microscopic cell images

The computer-based quantitative analysis of microscopic cell images provides important diagnostic information in clinical and experimental pathology. The arrangement of various cell structures can be described as texture. We developed a new approach to structural texture analysis. It assumes that texture consists of homogeneous regions (texture primitives). Texture can be regarded in a dual way--as a composition of regions or as a pattern composed of the regions' boundaries (lines). We implemented methods for the segmentation of regions and lines in grayscale images. The detection of regions is followed by a region-growing process to avoid an oversegmentation. The segmented regions and lines are stored in a uniform data structure which reflects their arrangement in the image. The presented methods were applied to study the chromatin distribution in cell nuclei and the development and differentiation of intermediate filaments in fetal liver cells.

Unsupervised texture segmentation using multichannel decomposition and hidden Markov models

In this paper, we describe an automatic unsupervised texture segmentation scheme using hidden Markov models (HMMs). First, the feature map of the image is formed using Laws' micromasks and directional macromasks. Each pixel in the feature map is represented by a sequence of 4-D feature vectors. The feature sequences belonging to the same texture are modeled as an HMM. Thus, if there are M different textures present in an image, there are M distinct HMMs to be found and trained. Consequently, the unsupervised texture segmentation problem becomes an HMM-based problem, where the appropriate number of HMMs, the associated model parameters, and the discrimination among the HMMs become the foci of our scheme. A two-stage segmentation procedure is used. First, coarse segmentation is used to obtain the approximate number of HMMs and their associated model parameters. Then, fine segmentation is used to accurately estimate the number of HMMs and the model parameters. In these two stages, the critical task of merging the similar HMMs is accomplished by comparing the discrimination information (DI) between the two HMMs against a threshold computed from the distribution of all DI's. A postprocessing stage of multiscale majority filtering is used to further enhance the segmented result. The proposed scheme is highly suitable for pipeline/parallel implementation. Detailed experimental results are reported. These results indicate that the present scheme compares favorably with respect to other successful schemes reported in the literature.

Texture classification and segmentation using wavelet frames

This paper describes a new approach to the characterization of texture properties at multiple scales using the wavelet transform. The analysis uses an overcomplete wavelet decomposition, which yields a description that is translation invariant. It is shown that this representation constitutes a tight frame of l(2) and that it has a fast iterative algorithm. A texture is characterized by a set of channel variances estimated at the output of the corresponding filter bank. Classification experiments with l(2) Brodatz textures indicate that the discrete wavelet frame (DWF) approach is superior to a standard (critically sampled) wavelet transform feature extraction. These results also suggest that this approach should perform better than most traditional single resolution techniques (co-occurrences, local linear transform, and the like). A detailed comparison of the classification performance of various orthogonal and biorthogonal wavelet transforms is also provided. Finally, the DWF feature extraction technique is incorporated into a simple multicomponent texture segmentation algorithm, and some illustrative examples are presented.