梯度矢量扩散控制实现边缘保持的彩色图像去噪

目的 在图像的获取过程中，由于受到噪声等因素影响，可能导致图像质量下降，给后期处理带来困难，为此提出一种梯度矢量扩散控制实现边缘保持的彩色图像去噪方法。方法 首先分析了彩色图像因灰度化带来的信息损失，为了更好地利用彩色图像信息，构造了RGB空间下的梯度矢量计算方法。其次分析了噪声邻域梯度矢量与边缘邻域梯度矢量间区域性结构差异，并指出现有扩散方程的不足，给出一种控制扩散矩阵的获取方法。最后通过推导矢量图像的边缘函数，给出了RGB空间下的PM方程，分解该模型去除法向扩散，并结合控制扩散矩阵改进边缘停止函数，以此获得更好的矢量扩散控制。结果 实验结果表明，采用这种方法得到的处理结果有着较高的信噪比，验证了该方法的有效性。结论 本文方法能够在去噪的同时，较好地保持图像对比度与边缘信息，具备一定的实用性。

Edge preserving denoising of color image through controlling the gradient vector

Objective Due to the impact of equipment and environmental, poor quality images could be generated inevitably in the process of image acquisition, and it could make more difficult for later processing. In this paper, an edge preserving denoising method of color image through controlling gradient vector is proposed. Method In order to make better use of color image information, information loss is analysis by color image to gray image firstly, and the calculation method of gradient vector in RGB space is proposed. Secondly, by analysising regional structure difference of noise gradient vector in neighborhood and edge gradient vector in neighborhood, the inadequacy with diffusion equation is point out, and a method of controlling the diffusion matrix is proposed. Finally, PM equation in RGB space is proposed through the edge function derived by vector images, normal diffusion is removed by decomposition of model and improved edge stopping function with the controlling the diffusion matrix can make better control. Result The results show the method has higher signal to noise ratio, and the effectiveness of it is verified. Conclusion This method can denoise image, and it could keep the image contrast and edge information at the same time, so it has some practicability.