Translator Disclaimer
30 October 2009 Weakly supervised specific object modelling for recognition
Author Affiliations +
Proceedings Volume 7496, MIPPR 2009: Pattern Recognition and Computer Vision; 74960Q (2009)
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
This paper describes how to construct a hyper-graph model from a large corpus of multi-view images using local invariant features. We commence by representing each image with a graph, which is constructed from a group of selected SIFT features. We then propose a new pairwise clustering method based on a graph matching similarity measure. The positive example graphs of a specific class accompanied with a set of negative example graphs are clustered into one or more clusters, which minimize an entropy function with a restriction defined on the F-measure( 2/(1recall+1/ precision) ). Each cluster is implified into a tree structure composed of a series of irreducible graphs, and for each of which a node co-occurrence probability matrix is obtained. Finally, a recognition oriented class specific hyper-graph(CSHG) is automatically generated from the given graph set. Experiments are performed on over 50K training images spanning ~500 objects and over 20K test images of 68 objects. This demonstrates the scalability and recognition performance of our model.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shengping Xia, Jianjun Liu, and Rui Song "Weakly supervised specific object modelling for recognition", Proc. SPIE 7496, MIPPR 2009: Pattern Recognition and Computer Vision, 74960Q (30 October 2009);

Back to Top