面向彩色手术显微图像的去噪算法改进

An Improvement of Noise Removal Arithmetic to the Color Microscopic Image

对于要求高保真的彩色手术显微图像,去除采集过程中引入的脉冲噪声是一项非常重要的任务。将自适应矢量中值滤波方法应用于彩色图像去噪,其效果非常理想。该方法可根据噪声干扰的情况自动选择滤波窗口的大小。先对图像各区域进行噪声检测,如果为非噪声区域,则不进行滤波;如果为噪声区域,则根据各区域受噪声污染状况自动确定滤波窗口尺寸。实验显示,采用自适应矢量中值滤波能有效滤除彩色显微图像的噪声,并能较好地保护边缘和细节,其性能较一般的矢量中值滤波方法有明显优势。

To a high fidelity color microscopic image, it is important to get rid of impulse noise which has been imported in collecting. The adaptive vector median filter has proved to be a highly effective tool, In the algorithm, based on the degree of noise interference, window size could be selected automatically. Firstly, noise detection is utilized to determine impulse noise whether or not .in the image. Right window is selected to remove noise. Result of experiments on the adaptive vector median filter show that the method can suppress noise effectively while preserving fine details very well and has better filtering performance than the regular vector median filter.