摘要
针对传统图像匹配算法存在特征信息少和误匹配率高的问题,提出基于SURF特征提取和FLANN搜索的图像匹配算法。通过Hessian矩阵获取图像局部最值,并使用不同尺寸特征描述器,同时处理尺度空间多层图像的向量特征,最后采用FLANN搜索算法进行特征匹配。试验表明,该算法比传统的图像匹配算法在效果和效率方面都表现得更好。
The traditional algorithm of image matching exist the problems of little feature informationand high rate false match. An image matching algorithm is presented based on SURF featureextraction and FLANN search. Firstly, the extremum value of local image is gotten using the Hessianmatrix. Secondly, the feature vector is simultaneously processed in multilayer image scale space byusing of different size feature description. Finally, the FLANN algorithm is used for feature matching.The experiments show that this algorithm is better than the traditional algorithm of image matching inthe aspect of effectiveness and efficiency.
出处
《图学学报》
CSCD
北大核心
2015年第4期650-654,共5页
Journal of Graphics
关键词
加速鲁棒特征
图像匹配
speed up robust features
Hessian
FLANN
image matching