A New Sample Consensus based on Sparse Coding (SCSC) for Improved Matching of SIFT Features on Remote Sensing Images

Abstract

In this paper, a new method is proposed for feature matching of remote sensing images using SCSC in order to improve image registration technique. To this end, SIFT features are used to select interesting points for image matching. The extract points contain some differences and similarities in two images captured from the same area (but different in sensor resolution, azimuth, elevation, contrast, illumination, etc.); in such a case, similar points should be extracted and other dissimilar should be eliminated. In this paper, we greatly improve matching between two images using the SCSC through checking points altogether. Moreover, the proposed method is shown to have better results than standard alternative methods such as RANSAC when the number of feature points is too much or have noise. However, it should be noted that for a low-noise and distortion rate, the proposed method and the RANSAC yield similar results. In general, the proposed method using sparse coding achieves a higher correct match rate than the SIFT algorithm. In order to illustrate this issue, the proposed method is compared to other updated matching and registration methods based on the SIFT algorithm. The obtained results confirm the accuracy of this claim and show that the proposed algorithm is accurated between 0.48% to 7.68% rather than SVD-RANSAC, Hoge, Stone, Foroosh, Leprince, Nagashima, Guizar, Youkyung, Lowe, Pre-registration , IS-SIFT, SPSA, Gong, Standard SIFT, IS-SIFT, UR-SIFT, Sourabh, Han methods.