Contour feature detection based on Gestalt rule and maximum entropy of neighborhood

A novel approach is presented to detect contour of object. Firstly, the zero-cross operator to imitate the visual receptive field is used to detect edge of image. Secondly, facing the large amount of noise in complex background, the neighborhood description operator is designed, and the neighborhood information of interesting point is analyzed as well. Then the contours of objects are acquired by combining with the Gestalt psychology theories. During the process, the maximum entropy and state transition probability of feature mode are introduced to ensure the effectiveness of contour detection. Finally, the experiments verify the validity of the proposed method.