Abstract
In this article, a bidirectional feature matching algorithm and two extended algorithms based on the priority k-d tree search are presented for the image registration using scale-invariant feature transform features. When matching precision of image registration is below 50%, the discarding wrong match performance of many robust fitting methods like Random Sample Consensus (RANSAC) is poor. Therefore, improving matching precision is a significant work. Generally, a feature matching algorithm is used once in the image registration system. We propose a bidirectional algorithm that utilizes the priority k-d tree search twice to improve matching precision. There are two key steps in the bidirectional algorithm. According to the case of adopting the ratio restriction of distances in the two key steps, we further propose two extended bidirectional algorithms. Experiments demonstrate that there are some special properties of these three bidirectional algorithms, and the two extended algorithms can achieve higher precisions than previous feature matching algorithms.
Highlights
Image registration is the way of overlaying two or more images of the same scene taken at different times, from different viewpoints
In the work done by Brown and Lowe,[10] the priority search is used only once where scaleinvariant feature transform (SIFT) features between two images are matched
In order to improve matching precision, in this article, we propose a bidirectional SIFT feature matching (BSFM) algorithm and two extended algorithms based on the priority search
Summary
Image registration is the way of overlaying two or more images of the same scene taken at different times, from different viewpoints. In the work done by Brown and Lowe,[10] the priority search is used only once where SIFT features between two images are matched. In order to improve matching precision, in this article, we propose a bidirectional SIFT feature matching (BSFM) algorithm and two extended algorithms based on the priority search. The key steps of the priority search can be summarized as follows[16]: Step 1: Apply branch-and-bound search in the descending down k-d tree (or subtree) and ceaselessly update the sorted list, until reaching a leaf node. We can see that the fundamental reason why the priority search is an efficient and approximate NN algorithm is that the NN should lie in the nearest bins (hyperrectangles) from query feature with high probability and the algorithm limits the number of the reached leaf nodes. If the ratio restriction of distances is adopted in the priority algorithm, the procedure of the priority algorithm is similar to the first step of BSFM1R and BSFM2R algorithms
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
