Saliency Object Detection Based on Regions Merging and Its Application in Image Retrieval

Abstract

In image retrieval, due to ignore the fact that different regions of the image have different levels of attraction to the human visual system in the traditional, so features are extracted of the entire image, result in the time is increased of the features matching. So we apply saliency object detection to image retrieval. However, extracting the saliency objects with complex background in the image is still a challenging problem. Thus we propose a region merging strategy to solve this problem. First, boundary super-pixels are clustered to generate the initial saliency map. Next, adjacent regions are merged by sorting the multiple feature values of each region. Finally, we get the final saliency map by merging regions by means of the distance from regions to the image center and the length of the boundary. After we apply the final saliency map to image retrieval. The experiments demonstrate that our method performs favorably on three datasets than state-of-art.