Homogeneity similarity based image denoising

This paper presents a homogeneity similarity based method, which is a new patch-based image denoising method. In traditional patch-based methods, such as the NL-means method, block matching mainly depends on structure similarity. The homogeneity similarity is defined in adaptive weighted neighborhoods, which can find more similar points than the structure similarity, and so it is more effective, especially for points with less repetitive patterns, such as corner and end points. Comparative results on synthetic and real image denoising indicate that our method can effectively remove noise and preserve effective information, such as edges and contrast, while avoiding artifacts. The application on medical image denoising also demonstrates that our method is practical.