Fairing Material Grain Contour Detection

On the basis of the modified Chan-Vese model and genetic algorithm, a new contour acquired method for image segmentation is presented. In the method, the raw contours were acquired by using the modified Chan-Vese model. The model is able to detect all the objects or details in the image. After that, the genetic algorithm was used to optimize the raw contours. The data points are respected as variables. The contours were then modeled as a continuous, nonlinear and multivariate optimization problem with many local optima. For this reason it is very difficult to reach a global optimum. In this paper, we convert the original problem into a discrete combinatorial optimization problem. The proposed method determines the appropriate contour location of the SiC/Al composite image automatically and simultaneously. The results show that our method is efficiency and effective.