Online ISSN:1349-8606
Progress in Informatics  
No.7 March 2010  
Page 43-52 PDF(1,092KB) | References
doi:10.2201/NiiPi.2010.7.6
Recognizing multiple objects based on co-occurrence of categories
Takahiro OKABE1, Yuhi KONDO2, Kris M. KITANI3, and Yoichi SATO4
1,2,4Institute of Industrial Science, The University of Tokyo
3Graduate School of Information Systems, The University of Electro-Communications
(Received: August 28, 2009)
(Revised: December 10, 2009)
(Accepted: January 4, 2010)
Abstract:
Most previous methods for generic object recognition explicitly or implicitly assume that an image contains objects froma single category, although objects from multiple categories often appear together in an image. In this paper, we present a novel method for object recognition that explicitly deals with objects of multiple categories coexisting in an image. Furthermore, our proposed method aims to recognize objects by taking advantage of a scene's context represented by the co-occurrence relationship between object categories. Specifically, our method estimates the mixture ratios of multiple categories in an image via MAP regression, where the likelihood is computed based on the linear combination model of frequency distributions of local features, and the prior probability is computed from the co-occurrence relation. We conducted a number of experiments using the PASCAL dataset, and obtained the results that lend support to the effectiveness of the proposed method.
Keywords:
Generic object recognition, context, co-occurrence, bag of features, regression, MAP estimation
PDF(1,092KB) | References

National Institute of Informatics is a member of CrossRef.
Go back HOME