Fast object recognition based on corner geometric relationship

The general object recognition algorithm which uses corner descriptions based on SIFT (Scale Invariant Feature Transform) and PCA (Principal Components Analysis) for patch matching and then eliminate the false matching pairs by RANSAC (RANdom SAmple Consensus) would have very heavy computation load. In this paper, we re-arrange the operating sequence of SIFT, PCA and RANSAC and utilizes the corner geometry relationships to pick up the robust initial pairs. Then, the parameters of the transformation matrix between the recognized image and the template image can be solved and all matching pairs can be obtained by the transformation matrix without SIFT-PCA calculation. Only very few SIFT and PCA calculation is required in our algorithm so that it is much faster than the traditional algorithms. From the experimental results, our algorithm shows very significant advantage over the traditional object recognition algorithm in computation time. Our algorithm only spent around one sixth to seventh computation time comparing to traditional algorithm.