Texture Feature Extraction Method Combining Nonsubsampled Contour Transformation with Gray Level Co-occurrence Matrix

Abstract

Gray level co-occurrence matrix (GLCM) is an important method to extract the image texture features of synthetic aperture radar (SAR). However, GLCM can only extract the textures under single scale and single direction. A kind of texture feature extraction method combining nonsubsampled contour transformation (NSCT) and GLCM is proposed, so as to achieve the extraction of texture features under multi-scale and multi-direction. We firstly conducted multi-scale and multi-direction decomposition on the SAR images with NSCT, secondly extracted the symbiosis amount with GLCM from the obtained sub-band images, then conducted the correlation analysis for the extracted symbiosis amount to remove the redundant characteristic quantity; and combined it with the gray features to constitute the multi-feature vector. Finally, we made full use of the advantages of the support vector machine in the aspects of small sample database and generalization ability, and completed the division of multifeature vector space by SVM so as to achieve the SAR image segmentation. The results of the experiment showed that the segmentation accuracy rate could be improved and good edge retention effect could be obtained through using the GLCM texture extraction method based on NSCT domain and multi-feature fusion in the SAR image segmentation.

Earlier detection of cancer regions from MR image features and SVM classifiers

“…The labels for MR images of these classes are normal, glioma, meningioma, metastasis, and astrocytoma. Here we use SVM with four kernels; they are RBF, linear, polynomial, and quadratic (Alexandros et al, 2006; He and Wu, ).…”

River extraction from Gaofen-1 Satellite images combined with relative total variation and stroke width transform

“…If the grayscale distribution of the target is large, a part of the target detection is lost. Texture feature segmentation has good applications in optical images 16,17 first used a gray-level co-occurrence matrix and nonsubsampling for multiscale and multidirectional texture extraction and then used the texture features as input to support vector machines for river extraction. Sghaier et al 18 extracted and differentiated rivers and lakes based on local texture features and global morphological operators.…”