An improved anisotropic diffusion model for detail- and edge-preserving smoothing
Pattern Recognition Letters
| Hi-index | 0.01 |
This paper puts forward a new edge-directed forward and backward anisotropic diffusion model for texture enhancement and edge sharpening of image. Since forward and backward diffusion cannot hold flow-like edges, and coherence enhancement diffusion cannot sharpen edges, our new model gets a new diffusivity, which combine the merits of these two methods. The new model adapts an image structure tensor like coherence enhancement diffusion for edge orientation, and defines eigenvalues based on edge orientation such that the new tensor has positive diffusivity in edge direction and negative diffusivity in gradient direction. Both theory analysis and numerical results show that the new model has better enhancement result than coherence enhancing diffusion and forward and backward diffusion.