An improved ORB feature extraction and matching algorithm based on affine transformation

As the key technology of image processing, image feature extraction and matching are widely used in face recognition, image stitching, and visual SLAM. Among them, ORB algorithm is widely adopted because of its advantage in real-time processing. However, the matching accuracy of the feature points extracted by ORB algorithm is still a concern for further applications. To address the problem, an improved ORB algorithm based on affine transformation was proposed. After FAST feature points are detected, the descriptors under different affine transformations are extracted from the feature points, and then the stable bits of the descriptor are extracted for feature matching. To further improve the accuracy of feature matching, an improved F-SORT algorithm is employed after feature matching. The improved F-SORT algorithm first groups the matched features in sequence order, and then further refines the matched feature pairs based on the angle, scale, and distance of the feature points. Experimental results verify the effectiveness of the algorithm regarding time efficiency and matching accuracy.