Weakly supervised specific object modelling for recognition

Shengping Xia, Jianjun Liu, Rui Song, Jun Zhang, Edwin R. HancockProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2009 · DOI

Abstract

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/<sub>(1recall+1/ precision)</sub> ). 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.
BibTeX
@inproceedings{xia2009weakly,
  author = {Shengping Xia and Jianjun Liu and Rui Song and Jun Zhang and Edwin R. Hancock},
  title = {{Weakly supervised specific object modelling for recognition}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2009},
  doi = {10.1117/12.831350},
}

Loading related content...

Figure