Denoising on Image Signal in Wavelet Basis with the VisuShrink Technique Using the Estimated Noise Deviation by the Monotonic Transform

웨이블릿 기저의 영상신호에서 단조변환으로 추정된 잡음편차를 사용한 VisuShrink 기법의 잡음제거

  • Published : 2004.04.01

Abstract

Techniques based on thresholding of wavelet coefficients are gaining popularity for denoising data because of the reasonable performance at the low complexity. The VisuShrink which removes the noise with the universal threshold is one of the techniques. The universal threshold is proportional to the noise deviation and the number of data samples. In general, because the noise deviation is not known, one needs to estimate the deviation for determining the value of the universal threshold. But, only for the finest scale wavelet coefficients, it has been known the way of estimating the noise deviation, so the noise in coarse scales cannot be removed with the VisuShrink. We propose here a new denoising method which removes the noise in each scale except the coarsest scale by Visushrink method. The noise deviation at each band is estimated by the monotonic transform and weighted deviation, the product of estimated noise deviation by the weight, is applied to the universal threshold. By making use of the universal threshold and the Soft-Threshold technique, the noise in each band is removed. The denoising characteristics of the proposed method is compared with that of the traditional VisuShrink and SureShrink method. The result showed that the proposed method is effective in denoising on Gaussian noise and quantization noise.

웨이블릿 변환 영역에서 계수 축소 방법의 잡음제거는 알고리즘의 단순함과 잡음제거 효과의 우수함으로 많이 사용되는 방법이다. 계수 축소 방법 중 VisuShrink는 데이터의 수와 잡음편차에 비례하는 universal 경계값을 사용하여 잡음을 제거하는 방법이다. 일반적으로 잡음편차가 알려져 있지 않으므로 universal 경계값 결정을 위해 잡음편차 추정이 필요하다. 그러나 잡음편차 추정 방법은 고주파 대역에서는 알려져 있으나 저주파 대역에 대해서는 알려져 있지 않으므로 기존의 VisuShrink 방법은 저주파 대역의 잡음을 제거할 수 없다. 본 논문에서는 단조변환에 의한 각 대역의 잡음편차를 추정하고, 추정된 편차에 가중값을 곱한 가중편차를 universal 경계값에 적용하여 최저주파 대역을 제외한 모든 대역의 잡음을 Soft-Threshold 기법으로 제거하였다. 그리고 잡음제거 특성을 비교하기 위해 기존의 VisuShrink방법 및 SureShrink방법과의 잡음제거 특성을 비교하였다. 비교 결과 본 논문에서 제시된 잡음제거 방법은 가우시안 잡음과 고압축 양자화 잡음에서 좋은 잡음 제거효과를 보였다.

Keywords

References

  1. Digital Image Processing Algorithms Ioannis Pitas
  2. Digital Image Processing W.K.Pratt
  3. Digital Image Processing R.C.Gonzalez;R.E.Woods
  4. Bayesian Interference in Wavelet-based Model An Introduction to wavelets B.Vidakovic;P.Muller;P.Muller(ed.);B.Vidakovic(ed.)
  5. Wavelets in Medicine and Biology A.Aldroubi;M.Unser
  6. Biometrika v.81 no.3 Ideal Soatial Adaptation by Wavelet Shrinkage D.L.Donoho;I.M.Johnstone
  7. Wavelets and Statistics Translation-Invariant De-Noising R.R.Coifman;D.I.Donoho;A.Antoniodis(ed.);G.Oppenheim(ed.)
  8. a Wavelet Tour of Signal Processing(2nd) S.Mallat
  9. J.A.J.A. v.91 no.432 Adapting to Unkonown Smoothness via Wavelet Shrinkage D.L.Donoho;I.M.Johnstone
  10. J. Roy. Statist. Soc. B v.58 Wavelet regression by Cross-Validation G.Nason
  11. Ann. Statist. v.24 no.2 Function Estimation via Wavelet shrinkage for Long-Memory Data Y.Wang
  12. Wavelets in Geophysics Simultaneous Noise Sippression and Signal Compression Using a Library of Orthonormal bases and the Minimum Description Length Criterion N.Saito;Foufoua-Georgiou(ed.);Kumar(ed.)
  13. Adavanced Signal Processing and Digitao Noise Reduction S.V.Vaseghi