A General and Effective Two-Stage Approach for Region-Based Image Retrieval

Content-based image retrieval (CBIR) has received substantial attentions for the past decades. It is motivated by the rapid accumulation of large collections of digital images which, in turn, create the need for efficient retrieval schemes. Many research works further utilize regional features to obtain the semantics of images for better retrieval performance. In this paper, a two-stage retrieval strategy is presented to improve the performance of region-based image retrieval (RBIR). In this approach, an image is first segmented into a fixed number of rectangular regions. Then, each region is represented by its low-frequency discrete cosine transform (DCT) coefficients in the YUV color space. At the first stage of retrieval, the threshold-based pruning (TBP) serves as a filter to remove those candidates with widely distinct features. At the second stage, a more detailed feature comparison (DFC) is conducted over the remaining candidates. In the experimental system, users can represent their region of interest (ROI) by selecting different strategies, setting parameter values, and/or adjusting the weights of features as the search progresses. The experimental results show that both efficiency and accuracy can be improved by using the proposed two-stage approach. [Life Science Journal 2010;7(3):73-80]. (ISSN: 1097-8135).