One-shot multi-set non-rigid feature-spatial matching

• Published in: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 3058 - 3065
• Main Authors: Torki, Marwan, Elgammal, Ahmed
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2010
• Subjects: Computer science; Computer vision; Deformable models; Embedded computing; Encoding; Geometry; NP-hard problem; Robustness; Scalability
• ISBN: 1424469848; 9781424469840
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2010.5540059

We introduce a novel framework for nonrigid feature matching among multiple sets in a way that takes into consideration both the feature descriptor and the features spatial arrangement. We learn an embedded representation that combines both the descriptor similarity and the spatial arrangement in a unified Euclidean embedding space. This unified embedding is reached by minimizing an objective function that has two sources of weights; the feature spatial arrangement and the feature descriptor similarity scores across the different sets. The solution can be obtained directly by solving one Eigen-value problem that is linear in the number of features. Therefore, the framework is very efficient and can scale up to handle a large number of features. Experimental evaluation is done using different sets showing outstanding results compared to the state of the art; up to 100% accuracy is achieved in the case of the well known `Hotel' sequence.