Recognition and Reconstruction of 3-D Objects Using Model-Based Perceptual Grouping

Input Image 3.0 Model In this papel; we addres.\' a new algorithm for recognition and reconstrttction of 3-D polyhedral objects, based on perceptual grouping and graph search technique. Perceptl~l grouping is peiformed in a model-basedframework, in ~vhich decision tree classifier is employedfor learning and retrieving geometric information of the 3-D model object. On the other hand, in order to extract the polygonal patch structure, initial grouping result is represented by a Gestalt graph. Polygonal patch hypotheses are then generated by graph search and verified by the consistency test ~vith the model. In the experiments, it is shown that the m~del-based grouping reduces the nltmber of the generated hypotheses efficiently, and fi4rthermore, robust recognition and reconstruction are achieved by means of the graph search technique. Figure 1. Blc:)ck diagram of the proposed algorithm