Typhoon Image Denoising in Curvelet Domain
Changjiang Zhang, Xiaoqin Lu · 2007
Employing discrete curvelet transform (DCT) and generalized cross validation (GCV), an efficient de-noising algorithm for typhoon cloud image is proposed. Asymptotical optimal threshold can be obtained, without knowing the variance of noise, only employing the known input image data. Having implemented DCT to an image, additive gauss white noise (GWN) can be reduced efficiently in the high frequency sub-bands of each decomposition level respectively. Experimental results show that the new algorithm can efficiently reduce the GWN in the satellite cloud image while well keeping the detail. In performance index and visual quality, the new algorithm is better than the de-noising algorithms based on discrete wavelet transform with soft threshold (DWT+SOFT) and discrete wavelet transform combining GCV (DWT+GCV).