摘要
针对传统图像匹配算法计算量大、耗时长等缺陷,提出一种基于SURF(speeded up robust features)的图像特征点快速匹配算法.首先对图像采用SURF算法提取特征点;然后通过Haar小波变换确定特征点的主方向和特征点描述子,使用优化的最近邻搜索算法(best bin first,BBF)进行特征点匹配;最后根据实际需要选取相似度最高的前n对匹配点进行对比实验.实验结果表明:该算法鲁棒性强,速度快,匹配准确性高,具有较大的应用价值.
With the shortcomings of the large calculation amount and long time consuming in the conventional image feature matching algorithms, a fast algorithm based on SURF （speeded up robust features） for image matching is presented in this paper. Firstly, exact feature points using SURF algorithm are extracted. For each feature point, the dominant orientation is assigned by com- puting Haar wavelet responses, and then the descriptors are generated. The feature points are matched using the optimized nearest neighbor search algorithm （best bin first, BBF）. Contrast experiment is carried out according to the actual need to select n most similar matchings. The results show that this algorithm meets the requirements of accuracy with a small amount of calculation and fast speed advantage.
出处
《扬州大学学报（自然科学版）》
CAS
CSCD
北大核心
2012年第4期64-67,共4页
Journal of Yangzhou University：Natural Science Edition
基金
国家自然科学基金资助项目(51273172)
