文章基本信息

标题：Convergence Analysis of Real-World Noisy Images in Blind Denoising
本地全文：下载
作者：Gulsher Ali ; Junaid Ahmed ; Bilal Tirmizi 等
期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2019
卷号：19
期号：2
页码：176-180
出版社：International Journal of Computer Science and Network Security
摘要：Most of the image denoising algorithms are tested on standard images with known noise process. It is assumed that the contaminating noise process is Additive White Gaussian Noise (AWGN). Moreover, intensity of the noise is also pre-defined. However, the real noise is much more complex than AWGN. In this paper, the blind image denoising is performed on real-world noisy images from Renoir dataset. The experiment is performed to analyze the convergence (finding optimum solution) performance of sparse or low rank approximation algorithms on removing real camera noise. Performance is evaluated in terms of peak signal-to-noise-ratio (PSNR) and structural similarity index measure (SSIM). Experimental results show that for denoising images with real camera noise the correlation based sparse representation approach keeps finding the most suitable atoms from dictionary and its performance keeps improving with the increasing dictionary subspace when compared to well-known KSVD algorithm.
关键词：Blind denoising;real-world noisy images;correlation based sparse representation.