Scale-Space and Edge Detection Using Anisotropic Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Picture Processing
Refining Initial Points for K-Means Clustering
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Texture Synthesis by Non-Parametric Sampling
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Region filling and object removal by exemplar-based image inpainting
IEEE Transactions on Image Processing
Kernel Regression for Image Processing and Reconstruction
IEEE Transactions on Image Processing
Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering
IEEE Transactions on Image Processing
Hi-index | 0.00 |
In this paper, a revised version of non-local means denoising method is proposed. Different from the original non-local means method in which the algorithm is processed on a pixel-wise basis, the proposed method using image patches to implement non-local means denoising. Given that some details, texture and structure information will be smoothed out when performing weighted averaging, we carry out a pre-processing procedure to classify the image patches into several clusters according to their feature similarities. Later, the weights needed in non-local means algorithm is calculated between image patches in the same cluster. By this means, the above mentioned detail, texture and structure can be preserved due to the redundancy in similar image patches. We illustrate the overall algorithm's performance via several experiments. The results indicate the effectiveness of the proposed method.