Paper Info
Title
A New Adaptive Thresholding in SVD for Efficient Image De-noising.
Abstract
This paper presents a new method for de-noising of images while preserving meaningful details such as blurred thin edges and low-contrast fine features using an adaptive threshold in singular value decomposition. The existing singular value decomposition technique utilizes a global fixed threshold for entire image and does not discriminate the noisy data from the image information for the images having uneven background. In this paper, different thresholds for the different structured portions of the image have been calculated in accordance with local gradient and gray level variance at each pixel position of those portions of the image. An optimal threshold has been estimated by the analysis of signal to noise ratios of the singular value decomposed images for different thresholds. Experimental results from a variety of test images have shown that the proposed thresholding scheme on singular value decomposed images can effectively smooth noisy background along with edge preservation and restoration of fine details in the enhanced image.
Year
DOI
Venue
2011
10.1007/978-81-322-0491-6_60
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON SOFT COMPUTING FOR PROBLEM SOLVING (SOCPROS 2011), VOL 2
Keywords
Field
DocType
Adaptive thresholding,Singular value decomposition,Image de-noising,Image enhancement
Singular value decomposition,Noisy data,Singular value,Pattern recognition,Computer science,Signal-to-noise ratio,Artificial intelligence,Pixel,Gray level,Balanced histogram thresholding,Thresholding
Conference
Volume
ISSN
Citations 
131
1867-5662
0
PageRank 
References 
Authors
0.34
1
3
Name
Order
Citations
PageRank
Nafis uddin Khan1182.76
K. V. Arya228928.09
Manisha Pattanaik33916.13