一种基于SURF和BRIEF的图像配准算法  

A image registration method based on SURF and BRIEF

作　　者：尚明姝 王克朝 SHANG Ming-shu;WANG Ke-chao(School of Information Engineering,Harbin Institute,Harbin 150080,China;School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China)

机构地区：[1]哈尔滨学院信息工程学院,黑龙江哈尔滨150080 [2]哈尔滨工业大学计算机科学与技术学院,黑龙江哈尔滨150001

出　　处：《微电子学与计算机》2020年第10期59-63,共5页Microelectronics & Computer

基　　金：国家自然科学基金(61977020);黑龙江省自然科学基金(LH2019F046)。

摘　　要：针对SURF算法特征描述复杂和匹配精确度不高的问题,提出先用SURF算法提取特征点,再计算其Harris响应值,剔除质量较差的特征点,使用BRIEF算法描述特征点,再用最近邻汉明距离匹配特征点.采用改进的K-means算法对数据分类,将数量较多的类里的匹配点作为正确匹配点保留.最后应用改进的RANSAC算法求变换矩阵.实验验证了算法性能.Considering SURF feature description having great computational complexity and feature matching not having high accuracy,an advanced image registration method is proposed.At first it uses SURF to extract the feature points from two images,then calculates Harris response values of every feature points.The feature points of low quality are canceled.Then BRIEF descriptor is utilized to characterize those feature points.Lastly the improved K-means algorithm is used to classify the data,and the classes with more matching points are reserved.The advanced RANSAC algorithm is used to compute the transform matrix between the two images.The experiments verify the algorithm’s efficiency.

关 键 词：图像配准 SURF BRIEF K-MEANS RANSAC 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]