计算机应用研究2012，Vol.29Issue(9)：3536-3539,4.DOI:10.3969/j.issn.1001-3695.2012.08.089
一种抗视角变换的SURF匹配算法
Anti-viewpoint-changing image matching algorithm based on SURF
摘要
Abstract
This paper proposed an improved SURF algorithm for image matching to bridge the gap of conventional SURF matching algorithm in matching feature points when the viewpoint change was great in the applications of image searching and object identification. The improved algorithm simulated possible perspective transformations from the original image, generated a set of simulated image sequence, and extracted SURF feature points in the sequence image. Then, the feature points of the simu lated images sequence were mapped to the original image. Composed the descriptors of the original image by the descriptors in original image and in the simulated images. Finally, used Euclidean distance criterion to get the matching point pairs. Experiment results show that this new algorithm increases the matched pairs of the image feature points, and overcomes the influence of viewpoint change (more than 60°) in image matching.关键词
SURF/视角变换/模拟图序列/图像匹配Key words
SURF/viewpoint change/simulating image sequence/image matching分类
信息技术与安全科学引用本文复制引用
李婕,邓德祥,石文轩,颜佳..一种抗视角变换的SURF匹配算法[J].计算机应用研究,2012,29(9):3536-3539,4.
