Image stitching based on ORB feature and RANSAC

In this paper, we introduced an image stitching algorithm which is based on ORB (Oriented FAST and Rotated BRIEF) feature and RANSAC (Random Sample Consensus) algorithm. First, we use ORB feature and brute force algorithm to find correspondences between images. Second, we apply the RANSAC algorithm to estimating homography robustly. Finally, the algorithm blends the images according to the homography and the image feathering algorithm was engaged to remove the visible seams due to exposure differences. From the results of experiments, we can draw a conclusion that the algorithm we proposed can stitch images seamlessly with a low computation time. © 2016, ICIC Express Letters Office. All rights reserved.