To search, Click below search items.


All Published Papers Search Service


Two-stage image denoising by Principal Component Analysis with Self Similarity pixel Strategy


K. John Peter, K. Senthamarai Kannan, S. Arumugan, G.Nagarajan


Vol. 11  No. 5  pp. 296-300


This paper presents an efficient image denoising scheme by using principal component analysis (PCA) with self similarity pixel strategy (SSS). For a better preservation of image local structures, a pixel and its nearest neighbors are modeled as a vector variable, whose training samples are selected from the local window by using self similarity driven strategy. Such an SSS procedure guarantees that only the sample blocks with similar contents are used in the local statistics calculation for PCA transform estimation, so that the image local features can be well preserved after coefficient shrinkage in the PCA domain to remove the noise. i.e. Color information present in the raw image can be transported from pixels where it is known to pixels where it is different based on local similarities. The image data obtain from PCA denoising procedure is passed through the SSS-PCA denoising procedure to further improve the denoising performance, and the noise level is adaptively adjusted in the second stage. Proposed algorithm find out the missing color components in the mosaic images captured by the CFA and improve the visual quality of the resulting output.


Demosaicking, Gradient, Mosaic Image, Local Similarities, Mosaic, CFA