仿射不变子空间特征及其在图像匹配中的应用.pdfVIP

第 43 卷第 2 期 红外与激光工程 2014 年 2 月 Vol.43 No.2 Infrared and Laser Engineering Feb.2014 仿射不变子空间特征及其在图像匹配中的应用 王国刚，史洪岩，汪 滢，袁德成 (沈阳化工大学 信息工程学院，辽宁 沈阳 100142) 摘 要： 提出了一种新的基于子空间的仿射不变图像匹配算法。 首先，分析了仿射不变特征空间的非线 性几何结构，给出了图像特征的仿射不变子空间表示模型。 其次，根据目标特征矩阵由它的正交投影矩阵 唯一确定这一特性实现特征的全局一致性匹配。最后，通过计算同一目标在仿射变换下的子空间几何距离 度量达到匹配识别的目的。模拟变换匹配实验和真实图像序列实验结果表明：所提出的匹配方法对仿射变 化下的图像目标匹配具有很好的适应性和较高的鲁棒性。 关键词： 目标匹配； 子空间； 仿射变换； 几何不变 中图分类号：TP391 文献标志码： A 文章编号： 1007-2276(2014)02-0659-06 Affine invariant subspace feature and its application in image matching Wang Guogang, Shi Hongyan, Wang Ying, Yuan Decheng (School of Information Engineering, Shenyang University of Chemical Technology, Shenyang 100142, China) Abstract: This paper presented a novel affine invariant image matching algorithm based on subspace theory. Firstly, the nonlinear geometry structure of the affine invariant feature space was explored and the affine invariant subspace image features were extracted; then the global consistent matching of shape feature was realized based on the theory that the feature matrix of target shape can be determined only by its orthogonal projection matrix; finally, the same target images were matched with affine transform through computing the subspace distance. Matching experiment results on simulated transformed real images and real images shows that the proposed algorithm exhibits higher capacity to affine transform and robust to perturbations. Key words: object matching; subspace; affine transform; geometric invariants 收稿日期 ：2013-06-10； 修订日期 ：2013-07-25 基金项目 ：辽宁省高等学校杰