Scale Invariant Feature Transform using oriented pattern

Abstract

Image matching plays an important role in many aspects of computer vision. Our proposed method is based on Scale Invariant Feature Transform (SIFT) which is one of the popular image matching methods. The main ideas behind our method are removing the excess keypoints, adding oriented patterns to descriptor, and decreasing the size of the descriptors. By doing these changes to SIFT, we would have oriented patterns of keypoints. In addition, the numbers of keypoints have been reduced and the places of keypoints would be selected more accurately, and also the size of the descriptors has been reduced.