{"references": ["I. K. Fodor, and C. Kamath, \"On denoising images using wavelet-based\nstatistical techniques,\" Lawrence Livermore National Laboratory LLNL\ntechnical report, UCRL JC-142357, 2001.", "I. Pitas, Digital Image Processing Algorithms and Applications, John\nWiley & Sons, Inc., 2000.", "Z. Devcic, and S. Loncaric, \"SVD block processing for non-linear image\nnoise filtering,\" Journal of Computing and Information Technology,\nVolume 7, Number 3, pp 255-259, 1999.", "S. Voloshynovskiy, O. Koval, and T. Pun, \"Wavelet-based image\ndenoising using non-stationary stochastic geometrical image priors,\" in:\nProceedings of SPIE Photonics West, Electronic Imaging 2003, Image\nand Video Communications and Processing V, Santa Clara, CA, USA,\nJanuary 20-24, 2003.", "S.K. Ponnappan, R.M. Narayanan, and S.E. Reichenbach, \"Effects of\nuncorrelated and correlated noise on image information content,\" in:\nProceedings of the International Geoscience and Remote Sensing\nSymposium, Sydney, Australia, 2001, pp. 1898-1900.", "A. Gyaourova, C. Kamath, and I. K. Fodor, \"Undecimated wavelet\ntransforms for image de-noising,\" Lawrence Livermore National\nLaboratory LLNL technical report, UCRL-ID-150931, 2002.", "S. Zhong, and V. Cherkassky, \"Image denoising using wavelet\nthresholding and model selection,\" in: Proceedings of the IEEE\nInternational Conference on Image processing, vol.3, Vancouver, BC,\nCanada, 2000, pp 262-265.", "A.R. Weeks, Fundamentals of Electronic Image Processing, SPIE\nOptical Engineering Press and IEEE Press, 1996.", "D. Harwood, M. Subbararao, H. Hakalahti, and L. Davis, \"A new class\nof edge preserving smoothing filters,\" Pattern Recognition Letters,\n5:155-162, 1987.\n[10] C. Garnica, F. Boochs, and M. Twardochlib, \"A new approach to edgepreserving\nsmoothing for edge extraction and image segmentation,\" in:\nProceedings of International Archives of Photogrammetry and Remote\nSensing, IAPRS Symposium, Amsterdam, The Netherlands, 2000.\n[11] M. A. Schulze, and J. A. Pearce, \"A morphology-based filter structure\nfor edge-enhancing smoothing,\" in: Proceedings of the 1994 IEEE\nInternational Conference on Image Processing, ICIP-94, Austin, Texas,\n13-16 November, 1994, pp. 530-534.\n[12] D. L. Donoho, and I. M. Johnstone, \"Ideal spatial adaptation via wavelet\nshrinkage,\" Biometrika, vol. 81, pp. 425-455, 1994.\n[13] L. Fan, L. Fan, and C. Tan, \"Wavelet diffusion for document image\ndenoising,\" in: Proceedings of the Seventh International Conference on\nDocument Analysis and Recognition, Volume II, Edinburgh, Scotland,\n2003.\n[14] S. Chang, B. Yu, and M. Vetterli, \"Image denoising via lossy\ncompression and wavelet thresholding,\" in: Proceedings of the IEEE\nInternational Conference on Image Processing, Washington, DC,\nOctober 26-29, 1997, pp 604-607.\n[15] S. Chang, B. Yu, and M. Vetterli, \"Spatially adaptive wavelet\nthresholding with context modeling for image denoising,\" in:\nProceedings of the IEEE International Conference on Image Processing,\nChicago, Illinois, October 04 - 07, 1998, pp 535-539.\n[16] D. L. Donoho, \"De-noising by soft-thresholding,\" IEEE Trans. Inform.\nTheory, vol. 41, pp. 613-627, 1995.\n[17] S. Chang, B. Yu, and M. Vetterli, \"Spatially adaptive wavelet\nthresholding with context modeling for image denoising,\" IEEE\nTransactions on Image Processing, Vol. 9, No. 9, pp 1522-1531, 2000.\n[18] I.K. Fodor, and C. Kamath, \"Denoising through wavelet shrinkage: an\nempirical study,\" Journal of Electronic Imaging, Volume 12, Issue 1, pp.\n151-160, 2003.\n[19] M.K. Mihcak, I. Kozintsev, K. Ramchandran, and P. Moulin, \"Lowcomplexity\nimage denoising based on statistical modeling of wavelet\ncoefficients,\" IEEE Signal Process. Lett. 6 (12), pp 300-303, 1999.\n[20] D. Cho, and T. D. Bui, \"Multivariate statistical modeling for image\ndenoising using wavelet transforms,\" Signal Processing: Image\nCommunication 20 , pp 77-89, 2005.\n[21] D. L. Donoho, and I. M. Johnstone, \"Adapting to unknown smoothness\nvia wavelet shrinkage,\" Journal of the American Statistical Assoc., vol.\n90, no. 432, pp.1200-1224, 1995.\n[22] S. Chang, B. Yu, and M. Vetterli, \"Adaptive wavelet thresholding for\nimage denoising and compression,\" IEEE Transactions on Image\nProcessing, Vol. 9, No. 9, 1532-1546, 2000.\n[23] D. D. Muresan, and T. W. Parks, \"Adaptive principal components and\nimage denoising,\" in: Proceedings of IEEE International conference on\nImage processing, Vol. 1, Barcelona, Spain, 14-17 September, 2003, pp\n101-104.\n[24] W. Sweldens, \"The lifting scheme: A custom-design construction of\nbiorthogonal wavelets,\" Appl. Comput. Harmon. Anal. 3(2), 186-200,\n1996.\n[25] W. Sweldens, \"The lifting scheme: A construction of second generation\nwavelets,\" SIAM J. Math. Anal. 29(2), 511-546, 1998.\n[26] I. Daubechies, and W. Sweldens, \"Factoring wavelet transforms into\nlifting steps,\" J. Fourier Anal. Appl. 4(3), 247-269, 1998.\n[27] R. Vargic, \"An approach to 2D wavelet transform and its use for image\ncompression,\" Radioengineering, Vol. 7, No. 4, 1-6, 1998.\n[28] A.R. Calderbank, I. Daubechies, W. Sweldens, and B. Yeo, \"Wavelet\ntransforms that map integers to integers,\" Appl. Comput. Harmon. Anal.\n5(3), 332-369, 1998.\n[29] A. Aldroubi, and M. Unser, Wavelets in Medicine and Biology, CRC\nPress, Inc., Florida, 1996.\n[30] G.Y. Luo, \"A novel technique of image quality objective measurement\nby wavelet analysis throughout the spatial frequency range,\"\nProceedings of SPIE, Vol. 5668 Image Quality and System Performance\nII, R. Rasmussen, Y. Miyake, Eds, 2005, pp. 173-184.\n[31] S. Saha, and R. Vemuri, \"An analysis on the effect of image features on\nlossy coding performance,\" IEEE Signal Processing Letters, Volume: 7,\npp 104-107, 2000."]}

The approach based on the wavelet transform has been widely used for image denoising due to its multi-resolution nature, its ability to produce high levels of noise reduction and the low level of distortion introduced. However, by removing noise, high frequency components belonging to edges are also removed, which leads to blurring the signal features. This paper proposes a new method of image noise reduction based on local variance and edge analysis. The analysis is performed by dividing an image into 32 x 32 pixel blocks, and transforming the data into wavelet domain. Fast lifting wavelet spatial-frequency decomposition and reconstruction is developed with the advantages of being computationally efficient and boundary effects minimized. The adaptive thresholding by local variance estimation and edge strength measurement can effectively reduce image noise while preserve the features of the original image corresponding to the boundaries of the objects. Experimental results demonstrate that the method performs well for images contaminated by natural and artificial noise, and is suitable to be adapted for different class of images and type of noises. The proposed algorithm provides a potential solution with parallel computation for real time or embedded system application.