Image Segmentation Based On Grey Relational Analysis And RBF

Traditional image segmentation based on Grey Relational analysis can eliminate the noise preferably,but it makes many mistake. This paper give a complex optimization method based on Grey Relational Analysis and RBF neural network.According to the prematurity matter of the Genetic Algorithm(GA),this paper give a complex optimization method based on k-means and Quantum Genetic Algorithm (QGA). First, accounting the center of the RBF neural network through k-means, then training the weights of RBF neural network by QGA. The express and renewal of quantum chromosome is used to improve the parallel of this procedure, so the problem of prematurity is solved, the fitness of network has been improved, and improving convergence speed of the network comparing the PSO-RBF and ACO-RBF. Finally, optimization of the RBF neural network is come true.Then extract the edge information by Grey Relational Analysis, and identify which pixel is noise,give these information to the optimized RBF neural network,it's good approach performance can rectify the mistake mentioned above,so the outcome of image segmentation procedure is better,and eliminate the noise more exactly. The simulation results confirm that segmentation effect of the proposed method is not only better than traditional methods, along with better noise immunity.