DefinePK

Abstract

Classification refers to assigning a physical object into one of the predefined categories. In texture classification, the goal is to assign an unknown sample image to one of a set of known classes. Texture classification is one of the challenging problems in image processing and computer vision. A major problem in textures in real world is often not uniform, due to changes in orientation, scale or other visual appearance. In addition, the degree of computational complexity of many of the proposed texture measures is very high. Important application of the texture classification include industrial and biomedical surface inspection, for example defects and disease, ground classification and segmentation of satellite or aerial imagery, segmentation of textured region in document analysis, and content based access to image databases. In this project an efficient method of texture classification using multi resolution transforms (Non Sub sampled Contourlet Transform) is proposed, which considers the features of texture images. Non Subsampled Contour let Transform has been widely recognized as a very useful tool in texture analysis, due to its optimal localization properties in both directional and frequency domain. The features (mean, standard deviation) are extracted from Non sub sampled Contourlet transform sub bands. The experimental result 85.79% achieved the classification rate of the proposed texture classification systems.