Image retrieval based on key-blocks

Abstract

In order to effectively introduce existing text-retrieval methods into content-based image retrieval, a novel image retrieval method based on key-block was presented incorporating the different sensitivity along variant directions of human visual system and block truncation coding (BTC). The key-block was firstly extracted by use of the principle of BTC according to the different direction of the texture distribution. After that, a model based on the weighted histogram was proposed combining the influence of the frequency for different kinds of key-block on the image. The method can achieved a higher efficiency because of integrating spatial distribution information and edge distribution information into image descriptor. Experimental results show that the proposed method has sound and robust retrieval performance especially for the images with the abundant texture information and edge information.