基于模糊中值滤波的椒盐噪声去除方法

Salt-and-pepper Noise Removal Based on Fuzzy Median Filtering

研究基于模糊中值滤波的椒盐噪声去除方法。通过比较图像各像素点的灰度值,定义基于图像梯度信息的各点被判别为噪声点的模糊隶属函数。利用此模糊隶属函数对中值滤波方法进行加权,得到了一种加权中值滤波器,可实现边缘处椒盐噪声的有效滤除。讨论这种模糊加权方法与其它先进滤波方法的结合途径,指出了其推广应用价值。最后利用数值实验验证本文方法的有效性,结果表明,相比于自适应中值滤波方法,本文方法得到的滤波图像在峰值信噪比及结构相似度方面均有明显提高。

Removal of salt-and-pepper noise using fuzzy median filter is proposed. By comparing the pixel values in the image, the fuzzy membership function of the candidates of noisy pixels is defined on the gradient of the image. By using this fuzzy membership function as the weight function, a new weighted median filter approach is proposed, which can remove the salt-and-pepper noise on image edges effectively. The combination of this weighed method with other advanced salt-and-pepper noise removal methods is also discussed, which proves the value of this new idea. Simulated experiments are employed to demonstrate the efficiency of the proposed method, and experiments results showed that the new method has higher peak signal to noise ratio （PSNR） and structure similarity （SSIM） than adaptive switch median filter （AMF）.