计算机技术与发展2012，Vol.22Issue(1)：98-102,5.
结合角点特征与SIFT特征的加速图像匹配
Combining Corner and SIFT Featrues to Accelerate Image Matching
摘要
Abstract
The use of keypoints to find correspondences across multiple images is a key step in many image processing and computer vision applications. Due to the large numbers of keypoints in an image,the feature matching rapidly becomes a bottleneck. In this paper,a novel method is presented to accelerate features matching by making comparisons only between the features of the same types. The first one is based on splitting the SIFT features into two types,Maxima-SIFT and Minima-SIFT features. In the second one,the SIFT feature combines the traditional corner-like features which use moment-derived corner patterns to extract keypoints and split sift features into different types use corner patterns. The presented experimental results show that the method has a big acceleration in the features matching performance compared to the original one without lose a noticeable precision and robustness.关键词
尺度不变特征变换/角点特征/关键点提取/快速特征匹配Key words
SIFT/corner feature/keypoints extraction/accelerated features matching分类
信息技术与安全科学引用本文复制引用
陈伟,刘丽..结合角点特征与SIFT特征的加速图像匹配[J].计算机技术与发展,2012,22(1):98-102,5.基金项目
国家自然科学基金项目(60873247) （60873247）
