CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2012 vol.34 Issue No.02 - February
Issue No.02 - February (2012 vol.34)
Myung Jin Choi , Two Sigma Investments, New York, NY, USA
Antonio Torralba , Comput. Sci. & Artificial Intell. Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA
Alan S. Willsky , Lab. for Inf. & Decision Syst., Massachusetss Inst. of Technol., Cambridge, MA, USA
There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. A context model can rule out some unlikely combinations or locations of objects and guide detectors to produce a semantically coherent interpretation of a scene. However, the performance benefit of context models has been limited because most of the previous methods were tested on data sets with only a few object categories, in which most images contain one or two object categories. In this paper, we introduce a new data set with images that contain many instances of different object categories, and propose an efficient model that captures the contextual information among more than a hundred object categories using a tree structure. Our model incorporates global image features, dependencies between object categories, and outputs of local detectors into one probabilistic framework. We demonstrate that our context model improves object recognition performance and provides a coherent interpretation of a scene, which enables a reliable image querying system by multiple object categories. In addition, our model can be applied to scene understanding tasks that local detectors alone cannot solve, such as detecting objects out of context or querying for the most typical and the least typical scenes in a data set.
probability, object recognition, image querying system, tree based context model, object recognition, contextual information, object categories, image features, probabilistic framework, Object recognition, Context modeling, Scene analysis, Object recognition, Computational modeling, Image processing, Markov processes, image databases., Object recognition, scene analysis, Markov random fields, structural models
Myung Jin Choi, Antonio Torralba, Alan S. Willsky, "A Tree-Based Context Model for Object Recognition", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.34, no. 2, pp. 240-252, February 2012, doi:10.1109/TPAMI.2011.119