An Eigenspace Based Approach For 3D Object Recognition

The aim of Computer Visual System is the interpretation for the existing "Visual" data, which can be utilized to complete tasks. Nowadays, object recognition has become an active research scopes, in need of a wide variety of practical applications, such as robots' work piece snatching at tasks, auto-navigation, auto-detection, tasks equipment and analysis of medical image, and so on. Presently many methods of object recognition are mainly based on the techniques of the template matching and the classification of the pick-up for the characteristic points of the geometric shape, which possess a large number of disadvantages. For instance, a kind of method that is based on the image matching directly compares the sum of gray of corresponding pixel in two images. But this discriminating method is not provided with the inflexibility of direction, scale and geometric aberrance, so it demands that object image must be of strong relativity and the tolerance to the image aberrance is considerably limited, which is one of the difficult points to the object recognition. This thesis mainly aiming at the method of algebraic character that is represented by SVD has done plenty of research work in the aspects of 3D object recognition and pose estimation. Because the algebraic character of an image reflects the image basis, although which is not quite straight in physical sense but important effect on the classification of the pattern, object recognition of taking out the algebraic character, which reflects the internal attribute of the object image, by algebraic transformation of the object image, now is a very potential direction in the field of object recognition.Firstly, this thesis lucubrates in the method theory of character space and does a lot of experiments and researches in the two steps, character expressing and measure of similarity. Realize the object recognition system based on the character subspace, which adopts the effective and ameliorative means to solve the problems existing in the course of recognition such as illumination and pose estimation, so enhances the robustness of recognition. After finishing arithmetic of the subspace object recognition, Considering All the object image can not get at one time We need computing a new SVD of image set matrix at getting a new object image, it will cost ( is the number of pixels in the image), so the complexity of computing time is too large. By studying the method of the subspace update more, we can find a fast and stable updating arithmetic of SVD. We also discuss more about the reservation of eigenvector and updating speed during the updating course.At last, combining the Eigenspace updating and the recognition method based on Eigenspace, we can figure out a recognition project learned in real time.