基于特征驱动的双向耦合扩散方程的图像去噪和边缘锐化

Feature-oriented coupled bidirectional flow equation for image denoising and edge sharpening

提出了一个新的能够同时去除图像噪声和锐化边缘的扩散方程模型。根据图像特征,例如边缘,纹理和局部细节,这个特征驱动的双向耦合扩散模型沿着等照度线(边缘)的梯度方向从前向扩散转变为后向(逆)扩散;而相反地沿切线方向实施前向扩散。为了消除前向力和后向力之间的冲突,将扩散方程分裂为一种耦合的形式;同时为了保持图像特征,利用图像的方向导数局部地调整非线性扩散系数。实验结果显示,本文算法能够在去除图像噪声的同时,有力地增强图像的特征。

A new type of diffusion process simultaneously denoising and sharpening images was considered. According to the image features such as edges, textures, and fine parts, the feature-oriented coupled bidirectional flow process could switch from a forward diffusion to a backward （inverse） one along the normal directions to the isophote lines （edges）, while a forward diffusion was performed along the tangent directions. To eliminate the conflict between the backward and the forward force, the diffusion process was splitted into a coupled scheme. In order to enhance image features, the nonlinear diffusion coefficients were locally adjusted according to the directional derivatives of the image. Experimental results demonstrate that the algorithm can substantially enhance features on denoising smoother areas of the image.