An improved image retrieval method based on SIFT algorithm and saliency map

Abstract

Image retrieval methods based on the Scale Invariant Feature Transform (SIFT) algorithm have good performance except for the characteristics of time-consuming and high dimension feature vectors. This paper realizes an improved image retrieval method combining saliency maps with SIFT. The saliency map algorithm is used to define and detect the visually salient image regions which will be used in feature extraction and feature matching. The experimental results show that the improved method can not only reduce the retrieval time, but also rule out the interference in image matching caused by the feature points in background.