ISSN : 2319-7323




INTERNATIONAL JOURNAL OF COMPUTER SCIENCE ENGINEERING


Open Access

ABSTRACT

Title : Image Denoising Based on Non-Local means Algorithm
Authors : N.Hemalatha, D.Ganesh Kumar
Keywords : Image denoising, impulse noise, gaussian noise, new impulse detector, nonlocal means (NL-means).
Issue Date : March 2014
Abstract : A Novel impulse noise detection technique is presented here.Edge-preseving and a fine detail of the image is a main problem, i.e. noise suppression. In order to remove Impulsive noise, a new noise detection mechanism and also filtering techniques using Non-Local means (NLM) is proposed in this paper. Impulse noise is a most common noise which affects the image quality during image acquisition, transmission, reception or storage and retrieval process in the area of image denoising. For detection, first, the proposed method is the robust outlyingness ratio (ROR) for measuring the impulse noise. Second, different rules are used to identify the impulsive noise based on the accurate deviation to the mid value in each group. To achieve the detection results more robust and more accurate, the strategy coarse-to-fine stage and the iterative method are used. The proposed work concentrates on removal of both impulsive noise and mixed noise from images. The results show that the proposed impulse detector is finer to most existing impulse detectors, and the ROR-NLM produces better results in terms of high peak signal-to-noise ratio (PSNR).
Page(s) : 101-106
ISSN : 2319-7323
Source : Vol. 3, No.2