基于曲率尺度空间的轮廓线匹配方法  

Contour matching method based on curvature scale space

作　　者：靳永刚 王凡[1] 胡小鹏[1] 

机构地区：[1]大连理工大学计算机科学与技术学院,辽宁大连116024

出　　处：《山东大学学报（理学版）》2014年第12期43-48,共6页Journal of Shandong University(Natural Science)

基　　金：国家自然科学基金资助项目(61272523)

摘　　要：基于曲率尺度空间(curvature scale space,CSS)理论,提出了一种匹配和识别存在仿射变化的平面曲线的方法。首先借助边缘检测算法提取图像轮廓,利用PCA白化算法消除轮廓线尺度、平移和切变的影响;然后对轮廓进行重采样并求取对应曲率尺度空间图的局部极值点;最后利用局部极值点向量数组作为轮廓线的描述符进行匹配。在MCD形状数据库的对比检索实验结果表明本文所提出的方法不仅有较高的检索率,而且对仿射变化具有良好的鲁棒性。An approach for matching and recognizing affine-distorted planar shapes was proposed, which is based on the theory of curvature scale space （CSS）. First, the contours were extracted by edge detection algorithm, and then use the PCA whitening method to eliminate the impact of scale, translation and shear. Second, the contour was resampled and the local maximum point was extracted. Final, the array of points was used as descriptor to match. The proposed meth- od was evaluated on MCD shape database, and the experimental results show that the method not only has the higher retrieval ratio but also is robust to affine transformation.

关 键 词：图像配准 轮廓线匹配 曲率尺度空间 PCA白化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]