Abstract—SIFT Feature with Relevance Feedback for Image Retrieval

SIFT Feature with Relevance Feedback for Image Retrieval Written by Administrator Wednesday, 16 March 2011 08:52 Last Updated Monday, 21 March 2011 07:32 In this paper, we used the Scale Invariant Feature Transform (SIFT) feature for image retrieval. SIFT descriptors are invariant to image scaling, transformation,rotation and partially invariant to illumination changes and affine, gives the local features of an image. Therefore, feature from the images can be extracted more accurately by using SIFT than color, texture, shape and spatial relations. SIFT descriptor vectors for each image is indexed by making the use of vocabulary tree. Further, relevance feedback technique is used to bridge the gap between low level features and high level concepts. The proposed method is tested on mixed database of Corel and Caltech 3000 images which shows a significant improvement in precision and average recall rate.