文章基本信息

标题：A NOVEL APPROACH FOR VIDEO RESTORATION USING GROUP-BASED SPARSE REPRESENTATION
本地全文：下载
作者：M.BAGYA LAKSHMI ; S.GOMATHI ; S.MALAIARASAN 等
期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2015
卷号：4
期号：2
页码：516-519
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Video restoration for blurred images is the significant challenge in Image processing. The video is restored using group based sparse representation. Video restoration is the operation of taking a corrupted/noisy video and estimating the clean original image. A Restoration method includes a motion-compensated de-noising. Digital compression artifacts and de-blocking are suppressed or masked. The group consists of non-local patches with similar structures and establishes a novel sparse representation modelling called Group Based Sparse Representation. Group Based Sparse Representation sparsely represents images in a unified framework. Thus this simultaneously enforces the local and non-local sparsity of self-similarity in images. For dictionary learning DCT technique is used for efficient restoration. Group Based Sparse Representation modelling performs peak signal-to-noise ratio. An experimental results show the performance of the proposed system. Thus this method is good in the video restoration concepts.
关键词：Denoising; image restoration; sparse representation; deblurring; inpainting.