An Improved Image Registration Algorithm based on SURF

Yujuan Zou ； Yong Chen

《Frontiers in Science and Engineering》 1卷9期 (2021/12) Pp. 21-25

https://doi.org/10.29556/FSE.202112_1(9).0004

摘要

Image stitching has become an important part of image processing and an increasingly popular research direction. Image registration is the core of image stitching. In order to overcome the performance imbalance of traditional algorithms, an improved image registration algorithm is proposed in this paper. Firstly, the algorithm detects the feature points based on Hessian matrix, and then describes the feature points by rBRIEF method. Finally, in the matching stage, the nearest neighbor ratio and next nearest neighbor algorithm are used for a rough matching, and the RANSAC algorithm is used to confirm the rough matching point pairs to eliminate false matching. The test results show that the improved surf image registration algorithm has certain efficiency and robustness.

關鍵字

Computer Vision ； Image Stitching ； Image Registration ； Hessian Matrix ； Speeded Up Robust Features (SURF)

參考文獻

Lee, Kyu-Yul, and Jae-Young Sim. "Warping residual based image stitching for large parallax." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020:8198-8206.

Li, Jing, et al. "Parallax-tolerant image stitching based on robust elastic warping." IEEE Transactions on multimedia 20.7 (2017): 1672-1687.

Babu, G., et al. "Enhanced SURF-and Wavelet-Based Underwater Image Stitching." Micro-Electronics and Telecommunication Engineering. Springer, Singapore, 2021. 351-359.

Tang, Qirong, et al. "Map Fusion Method Based on Image Stitching for Multi-robot SLAM." International Conference on Swarm Intelligence. Springer, Cham, 2021: 146-154.

Amalina, Neneng Nur, Kurniawan Nur Ramadhani, and Febryanti Sthevanie. "Nuclei Detection and Classification System Based On Speeded Up Robust Feature (SURF)." EMITTER International Journal of Engineering Technology 7.1 (2019): 1-13.