Study On Object Recognition Based On Shape

Shape is the inherence characteristic of an object in the image, and it is the important character used for the object recognition. So it is significant for object recognition based on shape.Firstly, general processing procedure of shape recognition is systematically reviewed. The whole process can be divided into three steps, including shape extraction, features extraction and classify or identify. The technologies and methods of shape extraction and recognition are studied in this thesis, and features extraction and applications are emphasized.Based on it, this paper presents a contour-based method of feature extraction and shape recognition. First the object contour is translated into a 1-D contour curve. Secondly the curve is smoothed to restrain the noise. The number of peaks of the curve is achieved as well as the areas which contained between adjacent peak-valley, then the latter is followed by Discrete Fourier Transformation (DFT). Then two kinds of features ate extracted which are invariant to translation, scaling and rotation transformations. By using the features, a two-stage recursive algorithm for recognition is proposed. Experimental results show that this method is simple and efficient.Then this paper works on the occluded shape recognition. First local invariant is extracted from the corners of the occluded object, which is used for local matching. Then we measure the similarity between the object and the models in image base, and determine the class of the object by the rule of max similarity. Experimental results show that this method is efficient.