基于微粒群算法和脉冲耦合神经网络的图像分割算法

脉冲耦合神经网络（Pulse Coded Neural Network，PCNN）在图像处理中得到了十分广泛的应用，但是其多个参数的设置给实际应用造成很大的困难。尤其是在图像分割中，不同类型的图像要求不同的分割参数，不同的参数对图像分割的结果影响很大。而微粒群优化算法（Partide Swarm Optimization，PSO）具有对参数自动寻优的优势，为此，将PSO和PCNN相结合，以改进的最大熵函数为适应度函数，提出了一种基于PSO和PCNN算法的图像自动分割算法。实验仿真结果验证了该方法的有效性，即不仅可以正确地实现图像分割，而且参数可以自动设置，省去了人工实验的麻烦，同时分割速度也有所提高。

An Image Segmentation Method Based on PSO Algorithm and PCNN

PCNN finds many application in image processing.Because the parameters greatly affect the performance of PCNN,finding the optimal parameters becomes an oneraous task.Especially in image segmentation,the parameters vary with the image that needs to process.PSO algorithm has the ability to find the best parameters,so a new image segmentation method was proposed that banded PSO and PCNN and it was used to segment the image automatically and successfully.The correctness and dependability of the methed is verified by experiment results,that is to say,the quality of the segmentation method is much better and time-consuming is less and parameters-setting is automatical.