计算机工程与应用2012，Vol.48Issue(8)：164-167,4.DOI:10.3778/j.issn.1002-8331.2012.08.047
基于空间约束的正则化流形学习影像匹配方法
New manifold regularization image matching algorithm based on spatial constraints
摘要
Abstract
A new image matching algorithm based on manifold regularization is proposed to efficiently match image pairs with large amount of data. The feature points of the two images are characterized the same underlying manifold, with the similarity constrain of the feature points coming from the different images calculated by the Manhattan distance between SIFT descriptors and spatial constrain calculated by distance between feature points from the same image which is the regularization of the objective function. The unified embedding of feature points can be obtained directly by solving the eigen-value problem. Test results indicate that the proposed method has a higher performance than SVD-SIFT and LE-SIFT methods, and this method has linear complexity, which is suitable for dealing with large number of feature points.关键词
空间约束/流形学习/正则化/曼哈顿距离Key words
spatial constraints/ manifold/ regularization/ Manhattan distance分类
信息技术与安全科学引用本文复制引用
李爱霞,关泽群,冯甜甜,周敏璐..基于空间约束的正则化流形学习影像匹配方法[J].计算机工程与应用,2012,48(8):164-167,4.基金项目
国家自然科学基金(No.41171327) （No.41171327）
同济大学人才基金资助项目(No.0200144055) （No.0200144055）
青年优秀人才培养行动计划(No.0250219047) （No.0250219047）
光华同济土木学院基金. （）
