Compression for the feature points with binary descriptors

Feature points, such as SIFT, BRISK, ORB, and FREAK, are effective for template matching, pattern recognition, and object alignment. However, since an image usually has 200-4000 feature points and the size of each descriptor is 512 or 256, an efficient way for encoding the descriptors and locations of feature points is required. In this paper, we propose an algorithm to encode the descriptors, locations, and angles of BRISK, ORB, and FREAK points efficiently. We apply both the global and local statistical characteristics and apply different reference points for the cases where the previous bit is 1 or 0. Moreover, the facts that feature points do not uniformly distribute and that two feature points with a short distance always have a small angle difference are also applied for compression. Simulations show that the proposed algorithm can much reduce the data sizes required for encoding feature points.