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 rstly 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 rst stage, matching, separates diierent objects and nds feature correspondences between the scene and each potential model object. The second stage, recognition, resolves inconsistencies among the results of matching to diierent objects and identiies 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 proba-bilistic formulation. Speciically, between-object constraints are encoded in the prior distribution modeled as a Markov random eld, and within-object constraints are encoded in the likelihood distribution modeled as a Gaussian. They are combined into the posterior distribution which de-nes the MAP solution. Experimental results are presented for matching and recognizing jigsaw objects under partial occlusion, rotation, translation and scaling.