Gray-level Co-occurrence Matrix Texture Features Research Articles

Computer‐aided diagnosis system for the detection of bronchiectasis in chest computed tomography images

AbstractA computer‐aided diagnosis (CAD) system has been developed for the detection of bronchiectasis from computed tomography (CT) images of chest. A set of CT images of the chest with known diagnosis were collected and these images were first denoised using Wiener filter. The lung tissue was then segmented using optimal thresholding. The Pathology Bearing Regions (PBRs) were then extracted by applying pixel‐based segmentation. For each PBR, a gray level co‐occurrence matrix (GLCM) was constructed. From the GLCM texture features were extracted and feature vectors were constructed. A probabilistic neural network (PNN) was constructed and trained using this set of feature vectors. The images together with the PBRs and the corresponding feature vector and diagnosis were stored in an image database. Rules for diagnosis and for determining the severity of the disease were generated by analyzing the images known to be affected by bronchiectasis. The rules were then validated by a human expert. The validated rules were stored in the Knowledge Base. When a physician gives a CT image to the CAD system, it first transforms the image into a set of feature vectors, one for each PBR in the image. It then performs the diagnosis using two techniques: PNN and mahalanobis distance measure. The final diagnosis and the severity of the disease are determined by correlating the diagnosis determined by both the techniques in consultation with the knowledge base. The system also retrieves similar cases from the database. Thus, this system would aid the physicians in diagnosing bronchiectasis. © 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 290–298, 2009

Computer-Aided Diagnosis of Soft-Tissue Tumors Using Sonographic Morphologic and Texture Features

The aim of this study was to develop a computer-aided diagnosis (CAD) system in assessing the sonographic morphologic and texture features of soft-tissue tumors. The retrospective study involved 114 pathology proven cases including 73 benign and 41 malignant soft-tissue tumors. The tumor regions were delineated by an experienced radiologist who was unknown to the pathologic result. Then, we applied 10 morphologic features and 6 gray-level co-occurrence matrix texture features to analyze the tumor regions. To classify the tumors as benign or malignant, we used two methods, a linear discriminant analysis with stepwise feature selection and a multilayer neural network with the back-propagation algorithm as classifiers. The classification performances are evaluated by the area A(z) under the receiver operating characteristic. Furthermore, four radiologists provided malignancy grades for all tumors in the comparison of the CAD system. In this analysis, the CAD system based on the combination of morphologic and texture feature sets can give the optimal CAD result by LDA with an accuracy of 89.5%, a sensitivity of 90.2%, a specificity of 89.0%, a positive predictive value (PPV) of 82.2%, negative predictive value (NPV) of 94.2%, and A(z) value of 0.96, and by the multilayer perception with an accuracy of 88.6%, a sensitivity of 90.2%, a specificity of 87.5%, a positive predictive value of 80.4%, negative predictive value of 94.2%, and A(z) value of 0.95. The A(z) values of the four radiologists were ranged between 0.74 and 0.86, and the optimal CAD results were shown the highest A(z) values than the four radiologists' rankings. This study has shown that performing the CAD system with both morphologic and texture features on sonography, can successfully distinguish between benign and malignant soft-tissue tumors. Moreover, it can also provide a second opinion for the tumor diagnosis and avert unnecessary biopsy.

Prediction of Malignant Breast Lesions from MRI Features: A Comparison of Artificial Neural Network and Logistic Regression Techniques

Dynamic contrast-enhanced magnetic resonance imaging is a clinical imaging modality for the detection and diagnosis of breast lesions. Analytic methods were compared for diagnostic feature selection and the performance of lesion classification to differentiate between malignant and benign lesions in patients. The study included 43 malignant and 28 benign histologically proved lesions. Eight morphologic parameters, 10 gray-level co-occurrence matrix texture features, and 14 Laws texture features were obtained using automated lesion segmentation and quantitative feature extraction. Artificial neural network (ANN) and logistic regression analysis were compared for the selection of the best predictors of malignant lesions among the normalized features. Using ANN, the final four selected features were compactness, energy, homogeneity, and Law_LS, with an area under the receiver-operating characteristic curve (AUC) of 0.82 and accuracy of 0.76. The diagnostic performance of these four features computed on the basis of logistic regression yielded an AUC of 0.80 (95% confidence interval [CI], 0.688-0.905), similar to that of ANN. The analysis also showed that the odds of a malignant lesion decreased by 48% (95% CI, 25%-92%) for every increase of 1 standard deviation in the Law_LS feature, adjusted for differences in compactness, energy, and homogeneity. Using logistic regression with z-score transformation, a model composed of compactness, normalized radial length entropy, and gray-level sum average was selected, and it had the highest overall accuracy, 0.75, among all models, with an AUC of 0.77 (95% CI, 0.660-0.880). When logistic modeling of transformations using the Box-Cox method was performed, the most parsimonious model with predictors compactness and Law_LS had an AUC of 0.79 (95% CI, 0.672-0.898). The diagnostic performance of models selected by ANN and logistic regression was similar. The analytic methods were found to be roughly equivalent in terms of predictive ability when a small number of variables were chosen. The robust ANN methodology uses a sophisticated nonlinear model, while logistic regression analysis provides insightful information to enhance the interpretation of the model features.

CO-OCCURRENCE PROBABILITIES AND WAVELET-BASED SPOOF FINGERPRINT DETECTION

Perspiration phenomenon is very significant to detect the liveness of a finger. However, it requires two consecutive fingerprints to notice perspiration, and therefore may not be suitable for real time authentications. Some other methods in the literature need extra hardware to detect liveness. To alleviate these problems, in this paper, to detect liveness a new texture-based method using only the first fingerprint is proposed. It is based on the observation that real and spoof fingerprints exhibit different texture characteristics. Textural measures based on gray level co-occurrence matrix (GLCM) are used to characterize fingerprint texture. This is based on structural, orientation, roughness, smoothness and regularity differences of diverse regions in a fingerprint image. Wavelet energy signature is also used to obtain texture details. Dimensionalities of feature sets are reduced by Sequential Forward Floating Selection (SFFS) method. GLCM texture features and wavelet energy signature are independently tested on three classifiers: neural network, support vector machine and K-nearest neighbor. Finally, two best classifiers are fused using the "Sum Rule''. Fingerprint database consisting of 185 real, 90 Fun-Doh and 150 Gummy fingerprints is created. Multiple combinations of materials are used to create casts and moulds of spoof fingerprints. Experimental results indicate that, the new liveness detection method is very promising, as it needs only one fingerprint and no extra hardware to detect vitality.

Application of computer vision for the prediction of cutting conditions in milling operations

Machining conditions such as speed, feed, and depth of cut significantly affect tool wear, which in turn affects the surface quality and thus this is an area of research interest. With the growing emphasis on industrial automation in manufacturing, vision techniques play an important role in many applications. One of these applications is texture analysis. Although this technique has been extensively researched it has only infrequently been used to predict the cutting conditions of machined surfaces. This paper introduces an application of computer vision to predict the cutting conditions in milling operations (feed, speed, and depth of cut) using grey-level co-occurrence matrix texture features. A software, named the Cutting Conditions Prediction in Milling has been developed in order to predict the cutting conditions from the captured images of machined surfaces. Three modules were developed to perform the prediction process and they are presented in this paper. The system was verified by predicting cutting conditions for various specimens and the maximum error between the predicted and the actual cutting conditions did not exceed ± 10.6 per cent.

Investigation of the cutting conditions in milling operations using image texture features

Texture is an important image feature in image analysis, which is related to qualitative properties of surfaces and corresponds to both brightness value and pixel locations. Image texture has been introduced into a wide range of applications such as metal surface analysis, textiles characterization, ultrasonic images processing, and food qualities evaluation. One of the most common methods for texture analysis is the grey level co-occurrence matrix (GLCM), which has a large number of texture features. In this work, an investigation of the relationship between GLCM texture features and the cutting conditions in milling operations (typically, feed, speed, and depth of cut) has been carried out. A vision system was employed to capture images for specimens with various known cutting conditions; then, the images were analysed by a software, which has been fully developed in-house to calculate 22 texture features. The relationship between each texture feature and the three cutting conditions are discussed and the correlation coefficients are introduced. The results showed that 15 texture features have good correlations with the feed, nine have good correlations with the speed, while only two have good correlations with the depth of cut.

Effect of probability-distance based Markovian texture extraction on discrimination in biological imaging

The effect of probability-distance based re-weighting of image texture features on their discrimination ability was evaluated in this study. A quadratic surface smoothing function was developed from the Bhattacharyya probability distance between two classes of images. The function was used as a re-weighting function for standard grey level co-occurrence matrix (GLCM) textural features in two cases. Case 1 involved 42 images of health and smokers’ lungs. Case 2 involved 144 images of well watered; partially water stressed and dry Rhacomitrium canescens plants. Multilayer perception (MLP) neural networks (NN) classifiers based on standard weighted and probabilistic-distance based re-weighted GLCM textural features were developed for each case. The classifiers were trained and tested using the leave-one-out and the cross-validation evaluation strategies. Probability-distance based re-weighting of GLCM textural features resulted in 37% and 39.22% reduction in true classification error for cases 1 and 2, respectively. It was concluded that re-weighting image texture features based on the probability distance between the classes involved, makes the GLCM texture analysis technique more discriminative and adaptive. This modification will help to overcome the fixed nature of GLCM features which is an area of weakness open to further improvement. Although GLCM features were used in this study, the method can be extended to other co-occurrence-based methods.

Comparison of Plant Water Stress Detection Ability of Color and Gray-Level Texture in Sunagoke Moss

Imaging is emerging as a novel technique for real-time and non-invasive stress diagnosis in plants. In this study, water stress detection ability of six texture features extracted using color co-occurrence matrix (CCM) and gray-level co-occurrence matrix (GLCM) methods were compared. Multi-layer perceptron neural network (MLPNN) models were developed and used to predict or classify water stress in five samples of Sunagoke moss (Rhacomitrium canescens) using the texture features. Hue-saturation-intensity (HSI) texture features had an average water stress prediction mean square error (MSE) of 0.0043. The average water stress prediction MSE of GLCM texture features was 0.0053. The CCM and GLCM texture features showed average water stress misclassification errors of 3.05% and 1.78%, respectively. Texture features extracted from HSI color space showed a higher ability and reliability to predict and classify water stress in the plant. By discarding the intensity component, the HSI texture features can be used to detect water stress in Sunagoke moss under natural lighting conditions. Use of hyperspectral reflectance imaging can enable this method to detect specific stress signatures for particular plants and make it a powerful biophysical, non-invasive, and pre-visual stress diagnosis method for a wide variety of stresses in plants.

An FPGA Based Coprocessor for GLCM and Haralick Texture Features and their Application in Prostate Cancer Classification

Grey Level Co-occurrence Matrix (GLCM), one of the best known tool for texture analysis, estimates image properties related to second-order statistics. These image properties commonly known as Haralick texture features can be used for image classification, image segmentation, and remote sensing applications. However, their computations are highly intensive especially for very large images such as medical ones. Therefore, methods to accelerate their computations are highly desired. This paper proposes the use of programmable hardware to accelerate the calculation of GLCM and Haralick texture features. Further, as an example of the speedup offered by programmable logic, a multispectral computer vision system for automatic diagnosis of prostatic cancer has been implemented. The performance is then compared against a microprocessor based solution.

Study of urban spatial patterns from SPOT panchromatic imagery using textural analysis

The long-time historical evolution and recent rapid development of Beijing, China, present before us a unique urban structure. A 10-metre spatial resolution SPOT panchromatic image of Beijing has been studied to capture the spatial patterns of the city. Supervised image classifications were performed using statistical and structural texture features produced from the image. Textural features, including eight texture features from the Grey-Level Co-occurrence Matrix (GLCM) method; a computationally efficient texture feature, the Number of Different Grey-levels (NDG); and a structural texture feature, Edge Density (ED), were evaluated. It was found that generally single texture features performed poorly. Classification accuracy increased with increasing number of texture features until three or four texture features were combined. The more texture features in the combination, the smaller difference between different combinations. The results also show that a lower number of texture features were needed for more homogeneous areas. NDG and ED combined with GLCM texture features produced similar results as the same number of GLCM texture features. Two classification schemes were adopted, stratified classification and non-stratified classification. The best stratified classification result was better than the best non-stratified classification result.