ABSTRACT

Content-based image retrieval system based on an efficient combination of both colours and features is explained in this paper. According to Kekre’s Transform, feature vectors are formed using acombination of row mean and column mean of both query as well as database images, to measure the extent of similarity using Euclidian distance. Similarly, HSV colour space quantifies the colour space intodifferent regions and thereby calculating its mean and Euclidian distance the colour vector can be derived. Taking mean of the Euclidian distances of both the algorithms better accuracy of the image retrieval process can be attained.