Segmentation Based Combined Wavelet-Curvelet Approach for Image Denoising

This work proposes the use of both the wavelet transform and the curvelet transform for denoising of images corrupted by AWGN. The wavelet reconstruction contains artifacts along the edges in an image. These edges can be captured efficiently by curvelets but curvelets are challenged by smooth regions where artifacts are largely visible. The desirable algorithm for denoising a noisy image should preserve the fine structures in the image and at the same time should not introduce artifacts. In this work the areas containing edges are denoised using curvelet transform while the remaining homogenous regions are recovered through wavelet transform. The areas containing edges and those that do not contain edges are segmented in the space domain by calculating a variance image and then thresholding it. The wavelet and curvelet denoising are inspired by methods in which the wavelet and curvelet coefficients are analyzed statistically and separated into two classes depending upon the probability whether a given coefficient contains a significant noise-free component or not. The algorithm is tested on some images for several noise levels and the results mostly show better performance than the recent methods which employ PDF based models. Also this method provides visually pleasant images as compared to the individual performances of either wavelets or curvelets.

[1]  I. Selesnick,et al.  Bivariate shrinkage with local variance estimation , 2002, IEEE Signal Processing Letters.

[2]  Gerlind Plonka-Hoch,et al.  The Curvelet Transform , 2010, IEEE Signal Processing Magazine.

[3]  Jacques Froment,et al.  Reconstruction of Wavelet Coefficients Using Total Variation Minimization , 2002, SIAM J. Sci. Comput..

[4]  Javier Portilla,et al.  Image Restoration Using Space-Variant Gaussian Scale Mixtures in Overcomplete Pyramids , 2008, IEEE Transactions on Image Processing.

[5]  Hossein Nezamabadi-pour,et al.  Image denoising in the wavelet domain using a new adaptive thresholding function , 2009, Neurocomputing.

[6]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[7]  R. S. Anand,et al.  PSO-based learning of sub-band adaptive thresholding function for image denoising , 2012, Signal Image Video Process..

[8]  Aleksandra Pizurica,et al.  A joint inter- and intrascale statistical model for Bayesian wavelet based image denoising , 2002, IEEE Trans. Image Process..

[9]  Aleksandra Pizurica,et al.  Image Denoising Using Mixtures of Projected Gaussian Scale Mixtures , 2009, IEEE Transactions on Image Processing.

[10]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  ANTONIN CHAMBOLLE,et al.  An Algorithm for Total Variation Minimization and Applications , 2004, Journal of Mathematical Imaging and Vision.

[12]  Robert D. Nowak,et al.  Platelets: a multiscale approach for recovering edges and surfaces in photon-limited medical imaging , 2003, IEEE Transactions on Medical Imaging.

[13]  Balázs Kégl,et al.  Image denoising with complex ridgelets , 2007, Pattern Recognit..

[14]  Aleksandra Pizurica,et al.  Estimating the probability of the presence of a signal of interest in multiresolution single- and multiband image denoising , 2006, IEEE Transactions on Image Processing.

[15]  I. Johnstone,et al.  Ideal spatial adaptation by wavelet shrinkage , 1994 .

[16]  Martin Vetterli,et al.  Spatial adaptive wavelet thresholding for image denoising , 1997, Proceedings of International Conference on Image Processing.

[17]  D. Donoho.  Wedgelets: nearly minimax estimation of edges , 1999 .

[18]  Wang-Q Lim,et al.  Sparse multidimensional representation using shearlets , 2005, SPIE Optics + Photonics.

[19]  Speckle reduction of SAR images using adaptive curvelet domain , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[20]  Robert D. Nowak,et al.  Wavelet-based statistical signal processing using hidden Markov models , 1998, IEEE Trans. Signal Process..

[21]  Aleksandra Pizurica,et al.  Context adaptive image denoising through modeling of curvelet domain statistics , 2008, J. Electronic Imaging.

[22]  Hayder Radha,et al.  Translation-Invariant Contourlet Transform and Its Application to Image Denoising , 2006, IEEE Transactions on Image Processing.

[23]  Martin Vetterli,et al.  Spatially adaptive wavelet thresholding with context modeling for image denoising , 2000, IEEE Trans. Image Process..

[24]  E. Candès,et al.  New tight frames of curvelets and optimal representations of objects with piecewise C2 singularities , 2004 .

[25]  Emmanuel J. Candès,et al.  The curvelet transform for image denoising , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[26]  D. L. Donoho,et al.  Ideal spacial adaptation via wavelet shrinkage , 1994 .

[27]  H. Chipman,et al.  Adaptive Bayesian Wavelet Shrinkage , 1997 .

[28]  B. Silverman,et al.  Wavelet thresholding via a Bayesian approach , 1998 .

[29]  Michael Elad,et al.  On the Role of Sparse and Redundant Representations in Image Processing , 2010, Proceedings of the IEEE.

[30]  Edward H. Adelson,et al.  Noise removal via Bayesian wavelet coring , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[31]  Laurent Demanet,et al.  Fast Discrete Curvelet Transforms , 2006, Multiscale Model. Simul..

[32]  N. Kingsbury.  Image processing with complex wavelets , 1999, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[33]  David L. Donoho,et al.  De-noising by soft-thresholding , 1995, IEEE Trans. Inf. Theory.