结合特征点与极谐变换的图像拼接  

Image mosaic combining feature point and polar harmonic transform

作　　者：李淑尚[1] 李雷达[1,2] 何霁野 宋万宝[3] 

机构地区：[1]中国矿业大学信息与电气工程学院,江苏徐州221116 [2]霍州煤电集团霍宝干河煤矿有限公司,山西霍州031400 [3]上海大屯能源股份有限公司物资贸易部,江苏徐州221611

出　　处：《计算机工程与应用》2013年第3期234-237,共4页Computer Engineering and Applications

基　　金：国家自然科学基金(No.60802077);中国博士后基金(No.20100471415);中国矿业大学青年科研基金(No.2009A022)

摘　　要：提出了一种新的结合特征点与极谐变换(Polar Harmonic Transform,PHT)的图像拼接算法。利用Harris角检测器提取图像中的特征点,计算特征点圆形邻域的PHT特征矢量,并通过计算欧氏距离作为特征点匹配的依据提取出初始特征点对。根据几何变换模型剔除伪匹配对,利用正确映射模型计算出变换参数,采用加权平均法得到图像的拼接结果。实验结果表明了算法的有效性。A new image mosaic method is proposed by combining feature point and Polar Harmonic Transform（PHT）. The feature points are extracted from the image using Harris detector, and the PHT feature vectors are computed over the circular neigh-boring area around the feature points. The initial feature point pairs are obtained by estimating the Euclidean distance between the PHT feature vectors. The spurious feature point pairs are removed according to the geometric transform model, and the transform parameters are computed through the correct mapping mode. Image mosaic is achieved using the weighed average method. Experimental results show the efficiencies of the proposed scheme.

关 键 词：图像拼接 特征点 极谐变换(PHT) 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]