A PCNN-Based Edge Detection Algorithm for Rock Fracture Images

Image segmentation has attracted the attention of researchers for many decades. Different approaches have been developed in order to find out the solution in many different segmentation situations. In this paper a novel method for rock fracture image using improved pulse coupled neural networks (PCNN) is presented. We apply progressive scan and region marked method to detect accurate edges of rock fracture images, the experiment results show that the proposed method can be used as a new image edge detection method. Compared to the traditional edge detection algorithms such as Canny operator and the other edge detection operators (e.g. vector gradient and MV), the proposed method can easily obtain the rock fracture images´ orientations, curvatures, lengths, apertures and other useful information.