Edge detection based on multi-structure elements morphology and image fusion

Edge detection is a fundamental and essential pre-processing step in applications such as image segmentation and computer vision. Conventionally, single edge detection method can only reflect the edge information from certain aspect. This paper deeply studies the edge detection methods of the noisy images and concentrates on the mathematical morphology methods. By analyzing and studying the theory of mathematical morphology, the paper constructs edge detection operations and analyzes the specialties of these operations and the structure elements. The new method of edge detection based on multi-structure elements morphology and image fusion is proposed. By simulation and comparing with the traditional edge detection operations, the proposed method not only can effectively eliminate the image noise, but also can effectively maintain good edge information.