• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.14-17
• /
• 2003

웨이블릿 변환 영역에서 잡음제거 방법 중 Visushrink 추정에 사용되는 경계값은 측정 데이터 수와 잡음편차에 비례하는 것으로 알려져 있으나 잡음편차가 알려지지 않은 경우 Donoho는 웨이블릿 변환 영역의 최고대역에서 잡음편차 추정 방법을 제시하였다. 본 논문에서는 분산이 데이터 수에 반비례함을 이용하여 threshold 기법을 이용하여 잡음제거 시 계산량을 감소를 목적으로 차 신호를 이용하여 측정데이터 수를 줄인 후 영상신호의 가우시안 잡음을 soft threshold 기법을 적용하고 이 기법의 실용성을 밝혔다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.281-284
• /
• 2000

이 논문은 웨이브릿 변환 영역의 백색 가우시안 잡음이 부가된 영상에서 최고 대역에서는 Donoho가 제시한 Visushrink 방법으로 잡음을 제거하고 최저대역을 제외한 나머지 대역들은 Monotonic 변환을 이용한 각 대역의 잡음편차를 추정하고 이를 VisuShrink 경계값에 적용하여 Soft-Threshold 기법으로 영상잡음을 제거하는 방법을 제안하였다. 실험 결과 이 논문에서 제시된 혼합방법에 의한 잡음 제거는 Donoho가 제시한 VisuShrink 방법보다 1㏈ 정도의 잡음제거 개선 효과가 있었다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.4
• /
• pp.255-265
• /
• 2007

In case of wavelet coefficients have correlation, in image signal denoising using wavelet shrinkage denoising method, the denoising effect for the image signal is reduced when the wavelet shrinkage denoising method is used. The coefficients of multiwavelet transform have correlation by pre-filters. To solve the degradation problem in multiwavelet transform, V Sterela suggested a new pre-filter for the Universal threshold or weighting factors to the threshold. In this paper, to improve the denoising effect in the multiwavelet transform, the coefficient normalizing method that the coefficient are divided by estimated noise deviation is adopted to the transformed multiwavelet coefficients in the course of wavelet shrinkage technique. And the thresholds of universal, SURE and GCV are estimated using normalized coefficients and tried to denoise by the wavelet shrinkage technique. We compared PSNRs of denoised images for each thresholds and confirmed the efficiency of the proposed method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.2
• /
• pp.111-118
• /
• 2004

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.