Iterative data adaptive anisotropic image filtering
ICMLC(2012)
摘要
This paper presents a novel data-adaptive anisotropic filtering technique built on top of an iterative scheme. This new technique can preserve the original significant structures while suppressing noises to the largest extent. To achieve this goal, dominant orientation information of all gradients is used to control the local kernel adaptively. This results in elongated and elliptical contours spread along the directions of the local edge structure. With these locally adapted kernels, the smoothing is mostly effective along the edges, rather than across them. Therefore details in the original input can be preserved. The performance of the proposed data-adaptive anisotropic filter together with its iterative scheme are compared with the conventional Gaussian filter, anisotropic diffusion filter, the structure-adaptive anisotropic filter, and the iterative kernel regression scheme. The experimental results on both simulated Gaussian and Poission noisy images indicate that the proposed method performs the best, and the iterative scheme can significantly improve the performance of the noise suppressing while delivering high computation efficiency.
更多查看译文
关键词
simulated gaussian noisy images,elliptical contours,image processing,performance improvement,iterative image filtering,image denoising,iterative data adaptive anisotropic image filtering,edge detection,elongated contours,local edge structure,data-adaptive anisotropic filter,filtering theory,performance evaluation,noises suppression,locally adapted kernels,iterative methods,adaptive local kernel control,simulated poission noisy images,gradient orientation information,noise
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络