An integrated color and texture feature based framework for content based image retrieval using 2D Wavelet Transform

This paper introduces an integrated color and texture feature based content based image retrieval using 2D Discrete Wavelet Transform (2D-DWT).Most of the image retrieval systems are still incapable of providing retrieval result with high retrieval accuracy and less computational complexity. To address this problem, combining color and texture features the effective integrated framework developed. In this approach, the color features of the query image and database images are computed and quadratic distance measure used as similarity metric to retrieve the relevant images and combined with the texture features extracted using 2D-DWT is compared with the query image and database image using euclidean distance measure. The proposed system combined features have been developed to provide efficient in terms of retrieval accuracy and precision. The precision improved from 67% to 95% and average recall rate of 67% to 95% for the general purpose database size of 10000 images also achieves better precision of 67% to 95% and average recall rate of 67% to 95% for the Brodatz album of 116 different textures of 1856 texture images.