Abstract
In this paper, a new approach for an object recognition together with the detection of its position and orientation from the 2-D gray scale image of 3-D objects in the scene is proposed. The description of a scene is given by the unprocessed gray-scale image which does of enhance the noise in the image and is more portable. GA is used to perform the search for a target object in the image by an exploration of the search space and exploitation of the best solutions of this search process. Also, in order to determine which object-model is the best, that is, which one provides the best recognition results criteria, three object-models, namely a frame model, a surface model, and a surface-strips model are examined in this research. From an analysis of the object-models sensitivity to position and orientation variations, the surface-strips model happened to provide more accurate and reliable recognition results. To examine the effectiveness of the proposed model-based object recognition method, several experiments of an object shape recognition together with the detection of its position and orientation using real gray-scale images are conducted.