2009 Fiscal Year Final Research Report

Object recognition based on co-occurrence of categories

Research Project

Project/Area Number	20700153
Research Category	Grant-in-Aid for Young Scientists (B)
Allocation Type	Single-year Grants
Research Field	Perception information processing/Intelligent robotics
Research Institution	The University of Tokyo
Principal Investigator	OKABE Takahiro The University of Tokyo, 生産技術研究所, 助教 (00396904)
Project Period (FY)	2008 – 2009
Keywords	コンピュータビジョン / 画像パターン認識
Research Abstract	Most previous methods for generic object recognition explicitly or implicitly assume that an image contains objects from a single category, although objects from multiple categories often appear together in an image. In this study, 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.

(5 results)