19 January 2009 Image feature matching with network flow: a global optimization method
Author Affiliations +
A new approach is presented for obtaining feature matching based on the identified features from images. Features which are described by high-dimension vectors are first extracted from a set of reference images and stored in a database, then the correspondence between similar features from different images are established by introducing the notion of a Min-cost K-flow Problem (MKP), which consists in finding a min-cost flow subject to the constraint that the flow value is K. The similarity function, which characterizes these vector components, can avoid the errors that come from different metrics of vectors. Finally, the K-flow is checked to reject ambiguous correspondence bi-directionally and automatically in accordance with the ratio of the matching cost. Experiments on three image sets demonstrate encouraging results.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xinying He, Xinying He, Qixiang Ye, Qixiang Ye, Yanmei Liu, Yanmei Liu, Guihong Zhou, Guihong Zhou, Jianbin Jiao, Jianbin Jiao, "Image feature matching with network flow: a global optimization method", Proc. SPIE 7257, Visual Communications and Image Processing 2009, 72570F (19 January 2009); doi: 10.1117/12.805865; https://doi.org/10.1117/12.805865


Back to Top