A Novel Region-Based Image Retrieval Algorithm Using Hybrid Feature

Having analyzed the drawbacks of image retrieval methods based on content, a novel region-based image retrieval algorithm using hybrid feature is proposed in this paper. The algorithm involves three steps: First, an image is segmented several regions by this algorithm. Second, spatial color distribution entropy is designed for each region, which takes not only the local color feature of the region into consideration, but also the spatial color distribution information of the region. Third, we use hybrid feature descriptor as feature vector of the regions to match images. With the robustness to rotation and translation, the algorithm avoids shortcoming of losing the location information in color histogram. Through experimental results and comparisons with other methods, the proposed algorithm is effective for image retrieval.