Abstract: In order to remove the pepper and salt noise in the gray scale image and keep the image details at the same time,a salt and pepper noise filtering algorithm is proposed.Firstly,the modified PCNN model is used to perform the ignition operation to locate the position of the noise pixel in the gray image.Then,the proposed symmetric detection median filter algorithm is used to filter the located noise point and the other pixel information remains unchanged.The simulation results show that the proposed method has better filtering performance than the existing filtering algorithm for the pepper and salt noise which noise density less than 70%.The algorithm can effectively filter out the noise and keep the edge detail of the image.The experimental results prove the effectiveness of the algorithm.