Image Texture Classification using Gray Level Co-Occurrence Matrix and Support Vector machine

Feature recognition plays an important role in the area of image processing and target based applications. In order to identify an object we must have its features in the form of a feature vector. This can be achieved by feature extraction. There are various ways of extracting features of an image. It can be based on color, texture or shape. This paper presents a novel method of texture features extraction using Gray Level Co-Occurrence Matrix and Support Vector machine. The texture classification is achieved by extracting the spatial relationship of pixel in the GLCM. The GLCM functions are used to characterize the texture of an image by calculating how often pairs of pixel with specific values and in a specified spatial relationship that occurs in an image. This created GLCM is then used for extracting statistical measures. The extracted features are used as an input to the Support Vector Machine (SVM) for classification. Experimental result shows that GLCM gives efficient result than wavelet and Gabor transform method.

Keywords:

Features Extraction , GLCM , SVM