Share Email Print

Proceedings Paper

Weakly supervised specific object modelling for recognition
Author(s): Shengping Xia; Jianjun Liu; Rui Song
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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/(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.

Paper Details

Date Published: 30 October 2009
PDF: 12 pages
Proc. SPIE 7496, MIPPR 2009: Pattern Recognition and Computer Vision, 74960Q (30 October 2009); doi: 10.1117/12.831350
Show Author Affiliations
Shengping Xia, National Univ. of Defense Technology (China)
Jianjun Liu, National Univ. of Defense Technology (China)
Rui Song, National Univ. of Defense Technology (China)

Published in SPIE Proceedings Vol. 7496:
MIPPR 2009: Pattern Recognition and Computer Vision
Mingyue Ding; Bir Bhanu; Friedrich M. Wahl; Jonathan Roberts, Editor(s)

© SPIE. Terms of Use
Back to Top