A two-stage probabilistic approach for object recognition
Assume that some objects are present in an image but can be seen only partially and are overlapping each other. To recognize the objects, we have to firstly separate the objects from one another, and then match them against the modeled objects using partial observation. This paper presents a probabilistic approach for solving this problem. Firstly, the task is formulated as a two-stage optimal estimation process. The first stage, matching, separates different objects and finds feature correspondences between the scene and each potential model object. The second stage, recognition, resolves inconsistencies among the results of matching to different objects and identifies object categories. Both the matching and recognition are formulated in terms of the maximum a posteriori (MAP) principle. Secondly, contextual constraints, which play an important role in solving the problem, are incorporated in the probabilistic formulation. Specifically, between-object constraints are encoded in the prior distribution modeled as a Markov random field, and within-object constraints are encoded in the likelihood distribution modeled as a Gaussian. They are combined into the posterior distribution which defines the MAP solution. Experimental results are presented for matching and recognizing jigsaw objects under partial occlusion, rotation, translation and scaling.
KeywordsObject Recognition Model Object Markov Random Field Curve Segment Gibbs Distribution
Unable to display preview. Download preview PDF.
- 1.N. Ayache and O. D. Faugeras. “HYPER: A new approach for the representation and positioning of two-dimensional objects”. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(1):44–54, January 1986.Google Scholar
- 4.R. Chellappa and A. Jain, editors. Markov Random Fields: Theory and Applications. Academic Press, 1993.Google Scholar
- 5.P. R. Cooper. “Parallel structure recognition with uncertainty: Coupled segmentation and matching”. In Proceedings of IEEE International Conference on Computer Vision, pages 287–290, 1990.Google Scholar
- 6.O. Faugeras. Three-Dimensional Computer Vision — A Geometric Viewpoint. MIT Press, Cambridge, MA, 1993.Google Scholar
- 8.W. E. L. Grimson. Object Recognition by Computer — The Role of Geometric Constraints. MIT Press, Cambridge, MA, 1990.Google Scholar
- 9.J. Hornegger and H. Niemann. “Statistical learning, localization and identification of objects”. In Proceedings of IEEE International Conference on Computer Vision, pages 914–919, MIT, MA, 1995.Google Scholar
- 12.S. Z. Li. Markov Random Field Modeling in Computer Vision. Springer-Verlag, New York, 1995.Google Scholar
- 14.K. V. Mardia and G. K. Kanji, editors. Statistics and Images: 1. Advances in Applied Statistics. Carfax, 1993.Google Scholar
- 17.Ullman. High-Level Vision: Object Recognition and Visual Cognition. MIT Press, 1996.Google Scholar