CONTENT BASED IMAGE RETRIEVAL USING COLOR, SHAPE AND TEXTURE

Abstract: Image Retrieval system is a novel application for searching and managing large scale image database. Content Based Image Retrieval (CBIR) is a technique which uses visual contents of image such as colour, shape and texture, etc. to search user required image from large scale image database according to user's requests in the form of a query image. Single feature represent only part of the image property so, to enhance the image retrieval effectively we are using multiple features such as colour, shape and texture to represent the whole image property.In this paper we proposed an algorithm which incorporates all three features such as colour, shape and texture to give the advantages of various other algorithms to improve the accuracy and performance of retrieval of images. The accuracy of HSV colour space based colour histogram based matching gives better retrieval result. The speed of shape based retrieval can be enhanced by considering approximate shape rather than the exact shape. Grey Level Co-occurrence matrix (GLCM) is used to extract the texture features of the images. The feature matching procedure is based on the Canberra distance.

Keywords: Content Based Image Retrieval(CBIR), Hue(H), Saturation(S), Value (V), Grey Level Co-Occurrence Matrix (GLCM).