基于一致性敏感哈希的高精确度图像匹配算法

High precision image matching algorithm based on consistency sensitive Hashing

针对基于特征点的图像匹配方式在复杂纹理场景中匹配效果不理想的问题,提出一种将加速稳健特征算法(SURF)与一致性敏感哈希匹配结合的图像匹配算法(CSH)。使用SURF算法对图像进行特征点提取,再以特征点为圆心构建特征区域,最后对特征区域使用CSH进行匹配,从而实现高精确匹配。为了进一步加快算法运行速度,对现有的SURF算法进行修改,在提取SURF特征点时去除了对于特征点方向的计算。仿真实验证明,算法较一般的特征算法在复杂纹理图像匹配中效果更佳,且较CSH算法效率提升了10%~15%。

The feature point-based matching methods suffer from unsatisfactory matching effect when employed in complex texture scenes.Therefore,a block based image matching method,which combines Speeded Up Robust Features(SURF)algorithm and Coherency-Sensitive Hashing(CSH)is proposed.This method is divided into three stages:firstly,using the SURF algorithm to extract feature points from the image;secondly,determining the feature areas with the SURF feature points as the center;thirdly,the feature areas are matched by CSH.In order to further speed up the method,SURF algorithm is modified to remove the calculation of the direction of feature points when extracting feature points.Experimental results show that the new method is better than the general image matching methods based on feature point in complex texture image matching.The efficiency of the proposed method has been increased by 10%to 15%compared with that of the CSH algorithm.