Using color information of target objects for web image retrieval

The color information for image retrieval has been used widely in many content-based retrieval systems However, traditional histogram-based color retrieval approaches suffer from lack of important objects knowledge of an image. It is thus impossible to recognize similar objects with different background colors in images using such approaches. In this paper, we present an approach to integrating color information with objects knowledge in order to obtain the major information of an image. In contrast to the previous ones, our approach uses the color histogram of particular objects in an image, rather than that of the whole image to retrieve relevant images. A prototype image retrieval system has been developed to demonstrate the effectiveness of our approach. The results have shown substantial improvement over previous approaches by using our approach.