Mining consistent correspondences using co-occurrence statistics

In this paper, we propose a mismatch removal method, which mines consistent image feature correspon-dences using co-occurrence statistics. The proposed method relies on a co-occurrence matrix that counts the number of pixel value pairs co-occurring within the images. Specifically, we propose to integrate the co-occurrence statistics with local spatial information, to preserve the consensus of neighborhood ele-ments. Then, a new measure based on co-occurrence statistics is defined for correspondence similarity, to preserve the consensus of neighborhood topology. After that, with the consensus of neighborhood el-ements and neighborhood topology, the mismatch removal problem is formulated into a mathematical model, which has a closed-form solution. Extensive experiments show that the proposed method is able to achieve superior or competitive performance on matching accuracy over several state-of-the-art com-peting methods. In addition, we further exploit the consensus of neighborhood elements and neighbor-hood topology to propose a novel guided sampling method, which can significantly improve the quality of sampling minimal subsets over state-of-the-arts for two-view geometric model fitting. (c) 2021 Elsevier Ltd. All rights reserved.