International Journal of Advanced Research in Computer Science and Software Engineering (IJARCSSE)
Content-Based Image Retrieval (CBIR) is useful for manipulating large amount of image databases and archives and for identifying and retrieving similar images. Extraction of invariant features is the basis of CBIR. In this paper, an effort has been made to create a hybrid feature database of four different classes of X-ray images namely chest, spine, foot and palm. This paper focuses on the problem of texture and shape feature extraction and feature database creation. The authors investigate texture feature and shape feature for CBIR by combining GLCM and ZM. GLCM is used for texture feature extraction and ZM extracts shape features.