Unsupervised Image Matching Based on Manifold Alignment
Unsupervised Image Matching Based on Manifold Alignment
复制标题
DOI：
10.1109/tpami.2011.229
复制
发表时间：
2012-08
影响因子：
23.6
通讯作者：
Yuru Pei;Fengchun Huang;F. Shi;H. Zha
中科院分区：
文献类型：
--
作者：
Yuru Pei;Fengchun Huang;F. Shi;H. Zha
本文提出了两个图像集之间的自动匹配问题，具有相似的内在结构和不同的外观，特别是当没有事先对应。提出了一种无监督流形对齐框架，通过相互嵌入空间中的映射函数建立数据集之间的对应关系。我们引入了一个局部相似性度量的基础上参数化的距离曲线来表示连接的一个点与其余的流形。通过将一个流形的距离曲线与另一个流形的曲线簇进行匹配，可以在没有手动交互的情况下找到一小组有效的特征对。为了避免潜在的混乱，在图像匹配，我们提出了一个扩展的仿射变换来解决嵌入空间中的非刚性对齐。可以同时获得相对紧密的排列和结构保存。对齐后具有最小距离的点对被视为匹配。我们将流形对齐应用于图像集匹配问题。不同的姿势，照明和身份的图像集之间的对应关系，可以有效地建立我们的方法。
This paper challenges the issue of automatic matching between two image sets with similar intrinsic structures and different appearances, especially when there is no prior correspondence. An unsupervised manifold alignment framework is proposed to establish correspondence between data sets by a mapping function in the mutual embedding space. We introduce a local similarity metric based on parameterized distance curves to represent the connection of one point with the rest of the manifold. A small set of valid feature pairs can be found without manual interactions by matching the distance curve of one manifold with the curve cluster of the other manifold. To avoid potential confusions in image matching, we propose an extended affine transformation to solve the nonrigid alignment in the embedding space. The comparatively tight alignments and the structure preservation can be obtained simultaneously. The point pairs with the minimum distance after alignment are viewed as the matchings. We apply manifold alignment to image set matching problems. The correspondence between image sets of different poses, illuminations, and identities can be established effectively by our approach.