一种针对图像脉冲噪声的改进中值滤波算法

针对中值滤波算法在图像脉冲噪声处理中存在的不足,提出一种新的改进中值滤波算法.该方法根据噪声图像的极值和像素点滤波窗口的局部信息对滤波窗口内像素点(含待处理像素点)是否为噪声点进行判断,剔除滤波窗口内的噪声点,然后根据新的滤波窗口及待滤波的中心像素点灰度值信息进行滤波操作.以迭代的方法更新噪声图像中的每个像素点,从而去除图像中的脉冲噪声.实验结果表明,与传统中值、加权中值、多级中值滤波方法相比,该方法能有效去除图像中的脉冲噪声,并保持图像细节特征完整.

Improved Median Filtering Algorithm for Image Impulse Noises

Aiming at the deficiencies of image impulse denoising of median filtering algorithm, a new improved median filtering algorithm is proposed. On the basis of the extreme values of noisy image and filtering window of pixel point (including pending pixel point), the noise points in the filtering window are eliminated, then the pending pixel point is filtered based on the new filtering window and the gray value of pending pixel point. Each pixel point of the noisy image is filtered by iterative method. The experimental results show that the proposed method can effectively remove the impulse noises in noisy image in comparison with traditional median filtering, weighted median filtering and multi-level median filtering, which maintains the detail characteristics of the image.