基于模糊边缘补足的自适应非局部均值图像去噪算法

Self-Adaptive Non-Local Means Image Denoising Algorithm Based on Fuzzy Edge Complement

针对传统非局部均值图像去噪算法对纹理细节处理保持不足的问题,提出一种结合模糊边缘补足(FEC)的非局部均值图像去噪算法。利用FEC算法检测出图像的边缘纹理特征图像;基于此自适应选择相似性权重参数,有针对性地对边缘纹理区域和平坦区域进行不同程度的平滑,以防止边缘细节信息的过平滑;用边缘的结构相似性改进非局部图像块的相似性权重,加强相同区域像素的贡献而削弱不同区域像素的贡献,从而达到更好地保持纹理细节的作用。实验结果表明:该方法能够很好地达到去除噪声的效果,同时还能保持更多的纹理细节特征和几何结构特征。

In view of the holding unsatisfactory effects of the traditional non-local means algorithm for texture details, an improved non-local means denoising algorithm combined with fuzzy edge complement （FEC） is proposed. The edge texture feature image is detected by the FEC algorithm. The similarity weight parameter is chosen adaptively according to the edge texture feature, and the edge texture region and the flat region are smoothed for different degrees pertinently, which prevents the edge texture information from being lost. The similarity weights of non-local image blocks are improved using the structural similarity of edges. The effects of pixels in the same area are increased, and those in different areas are reduced. Thus, the better texture hold effects can be achieved. Experimental result indicates that the image denosing can be effectively achieved by this method. Meanwhile, the more texture detail features and geometrical structural features are persevered.