An Efficient Curvelet Framework for Denoising Images


electrical engineering, sirjan university of technology


Wiener filter suppresses noise efficiently. However, it makes the out image blurred. Curvelet preserves the edges of natural images perfectly, but, it produces visual distortion artifacts and fuzzy edges to the restored image, especially in homogeneous regions of images. In this paper, a new image denoising framework based on Curvelet transform and wiener filter is proposed, which can stop noise better than these methods. The performance of introduced scheme is evaluated in terms of two important denoising criteria, PSNR and SSIM on standard test images in different noise levels. Three famous thresholding ‘soft’, ‘semisoft’ and ‘hard’ are applied to noisy images and results are fused by the wavelet transform to form restore images. Our framework outperforms the curvelet transform denoising by %6.3 in terms of PSNR and %5.9 in terms of SSIM for ‘Lena’ image. The visual outputs show that false artifacts, parasite lines and the blurring degree of output images, are reduced significantly. The obtained results reveal the superiority of our framework over recent reported methods.