A research of feature-based image mosaic algorithm

Due to the stitching precision and speed of existing image mosaicing technique, this paper summarizes three common based on Feature matching algorithm: Harris corner detection algorithm, SIFT (Scale Invariant Feature Transform) algorithm, SURF ( Speeded-Up Robust Features ) algorithm. This paper describes the principle of three algorithm respectively. The performance of the algorithm are compared for corresponding points computing time and stitching precision. Harris algorithm´s perform of extracting angular points was worst, and lowest effectiveness of finding corresponding points. SIFT presents its stability for for rotation and scale in most situation, although it is slow. SURF is the fastest one with good performance as same as SIFT.