Denoising of images has been a successful research topic for various image processing applications. Image denoising is
basically restoration of images, where the unwanted noises causing degradations are removed to obtain a visually effectual high quality
image. The majority existing image denoising algorithms failed to focus on the diminishing edges whilst noise reduction. The net
effect is the low quality denoised image. This paper tackle the edge preserving problem by presenting SAIST (Spatially Adaptive
Iterative Singular-value Thresholding) image denoising algorithm incorporating bilateral filtering. In this work a two-fold approach is
adapted. First is preserving edges through bilateral filtering. A non- maximum suppression on the smoothed image and morphological
dilation to stretch the edges are performed. Second is image denoising using iterative regularization and singular valued decomposition
(SVD) for estimating signal variances. The pragmatic results and better computational efficiency do better than several state-of-theart
image denoising algorithms.
Published In:IJCSN Journal Volume 6, Issue 3
Date of Publication : June 2017
Pages : 320-324
Figures :05
Tables : 01
Renju Mohan : received the B. Tech degree in Computer Science
and Engineering from Kerala University, India, in 2011, and
currently doing M. Tech in Computer Science and Engineering in
MET’S School of Engineering, Mala – APJ Abdul Kalam
Technological University, Kerala, India.
Sruthy M . S : is an Assistant professor in MET’S School of
Engineering Mala, Thrissur, Kerala. Received the B.Tech degree
from Matha Engineering College Paravur, Kerala and M.E from
Maharaja Institute of Technology. She has more than 4 years of
teaching experience. Subject of interest are Parallel Processing
and Architecture, Programming, Computer-Organization.
Dr. D. Loganathan : is a Professor and Head of Computer Science
and Engineering department in MET’S School of Engineering,
Mala, Trissur, Kerala. After his B.E., and M.E degree, he
accomplished a doctoral degree from Anna University, Chennai,
India. He has more than 20 years of teaching experience and
having 8 years of research experience in engineering field. His
research interest includes Wireless Communication, Wireless Ad
hoc Networks and Image Processing. He has published several
research papers in various international journals.
An improved method of image denoising while preserving
edges is proposed here. In this method the Canny edge
detection with Bilateral filtering is used to extract and
preserve edges respectively. Bilateral filtering includes
smoothing whilst preserving edge, which is non-iterative
in manner. This particular technique defines weights
based on the chosen pixel and nearby pixel.
A well-known segmentation method called mean shift
segmentation is used for clustering pixels into different
patches. For performing denoising after preserving edges,
SAIST (Spatially adaptive iterative singular-value
thresholding) is used. The iterative regularization
technique, noise variance update, singular-value
decomposition (SVD) is collaborated to get desired result.
Excellent experimental results have been obtained for
proposed image denoising.
[1] H. Liu, N. Klomp, and I. Heynderickx, “A perceptually
relevant approach to ringing region detection,” IEEE
Trans. Image Process., vol. 19,no.6,pp. 1414–1426, Jun.
2010.
[2] J. Canny, “A computational approach to edge detection,”
IEEE Trans. Pattern Anal. Mach. Intell., vol. 8, no. 6, pp.
679–698, Nov. 1986.
[3] C. Tomasi and R. Manduchi, “Bilateral filtering for gray
and color images,” in Proc. 6th Int. Conf. Comput. Vis.,
Jan. 1998, pp. 839–846
[4] D. Comaniciu and P. Meer, “Mean shift: A robust
approach toward feature space analysis,” IEEE Trans.
Pattern Anal. Mach. Intell., vol,24, no. 5, pp. 603–619,
May 2002. [5] V. Katkovnik, A. Foi, K. Egiazarian, and J. Astola,
“From local kernel to nonlocal multiple-model image
denoising,” Int. J. Comput. Vis., vol. 86,no. 1, pp. 1–32,
2010.
[6] M. Elad and M. Aharon, “Image denoising via sparse
and redundant representations over learned
dictionaries,” IEEE Trans. Image Process., vol. 15, no.
12, pp. 3736–3745, Dec. 2006.
[7] S. Osher, M. Burger, D. Goldfarb, J. Xu, and W. Yin,
“An iterative regularization method for total variationbased
image restoration,” Multiscale Model. Simul.,
vol. 4, no. 2, pp. 460–489, 2005.
[8] P Anakha Satheesh, Dr. D. Loganathan, 2016, De-
Speckling of SAR Images Based on Optimal Basis
Wavelet via Patch Ordering, GJERM, vol 3(6), pp 49-
55.
[9] S. Yang, L. Zhao, M. Wang, Y. Zhang, and L. Jiao,
“Dictionarylearning and similarity regularization based
image noise reduction,” J. Vis. Commun. Image
Represent., vol. 24, no. 2, pp. 181–186, 2013.
[10] J. Cai, E. Candes, and Z. Shen, “A singular value
thresholding algorithm for matrix completion,” SIAM J.
Optim., vol. 20, no. 4, pp. 1956–1982, 2010.
[11] J. Mairal, F. Bach, J. Ponce, G. Sapiro, and A.
Zisserman, “Non-local sparse models for image
restoration,” in Proc. IEEE 12th Int.Conf.Comput. Vis.,
Jun. 2009, pp. 2272–2279.
[12] G. Gilboa and S. Osher, “Nonlocal operators with
applications to image processing,” Multiscale Model.
Simul., vol. 7, no. 3, pp. 1005–1028, 2008.
[13] M. Charest, M. Elad, and P. Milanfar, “A general
iterative regularization framework for image
denoising,” in Proc. 40th Annu.Conf.Inf.Sci.Syst.,
2006, pp. 452–457.
[14] J. Mairal, F. Bach, J. Ponce, G. Sapiro, and A. Zisserman,
“Non-local sparse models for image restoration,” in Proc.
IEEE 12th Int.Conf.Comput. Vis., Jun. 2009, pp. 2272–
2279.
[15] J. Bobin, J. et.al, Morphological component analysis: an
adaptive thresholding strategy,” IEEE Trans. Image
Process., vol. 16, no. 11, pp. 26752681,Nov.2007.
