A Local Feature Based Robust Image Retrieval Algorithm

Color histograms lack spatial information and are sensitive to intensity variation, color distortion and cropping. As a result, images with similar histograms may have totally different semantics. The region-based approaches are introduced to overcome the above limitations, but due to the inaccurate segmentation, these systems may partition an object into several regions that may have confused users in selecting the proper regions. Based on multi-scale Harris Laplace detector, a robust image retrieval scheme using the color histogram of local feature regions is proposed in this paper. Experimental results show that the proposed color image retrieval is more accurate and efficient in retrieving the user-interested images. Especially, it is robust to some classic transformations.