Hybrid wavelet transform filter for image recovery

Wavelet denoising techniques are used to remove additive Gaussian noise by thresholding the wavelet coefficients. Like other transform based filters, wavelet shrinkage methods provide blur or visual artifacts that are exhibited in the neighborhood of image edges. The motive for implementing the hybrid wavelet transform filter (HWTF) is to provide a discriminate smoothing operator for noise removal. The undesirable smoothing effects can be minimized by performing two stages of wavelet de-noising and gray scale transform methods. The experimental results show that the proposed nonlinear wavelet filtering for noise reduction is an efficient technique to improve image quality.

[1]  D. Donoho,et al.  Translation-Invariant DeNoising , 1995 .

[2]  Lori E. Lucke,et al.  Multi-level adaptive fuzzy filter for mixed noise removal , 1995, Proceedings of ISCAS'95 - International Symposium on Circuits and Systems.

[3]  David L. Donoho,et al.  Nonlinear Wavelet Methods for Recovery of Signals, Densities, and Spectra from Indirect and Noisy Da , 1993 .

[4]  Wenyuan Xu,et al.  On ill-posed anisotropic diffusion models , 1995, Proceedings., International Conference on Image Processing.

[5]  Sanjit K. Mitra,et al.  Adjustable quadratic filters for image enhancement , 1997, Proceedings of International Conference on Image Processing.

[6]  I. Johnstone,et al.  Adapting to Unknown Smoothness via Wavelet Shrinkage , 1995 .

[7]  Stéphane Mallat,et al.  Multifrequency channel decompositions of images and wavelet models , 1989, IEEE Trans. Acoust. Speech Signal Process..

[8]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[9]  G. Nason Choice of the Threshold Parameter in Wavelet Function Estimation , 1995 .

[10]  Jong-Sen Lee,et al.  Digital image smoothing and the sigma filter , 1983, Comput. Vis. Graph. Image Process..

[11]  R. DeVore,et al.  Fast wavelet techniques for near-optimal image processing , 1992, MILCOM 92 Conference Record.

[12]  Ioannis Pitas,et al.  Adaptive LMS L-filters for noise suppression in images , 1996, IEEE Trans. Image Process..