30 October 2009 Study of blind image restoration algorithm based on non-negative independent component analysis
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 749544 (2009) https://doi.org/10.1117/12.831426
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
Blind image restoration is a great part of image processing, which refers to the technology field that study how to restore the original image from the observed image without sufficient prior knowledge about the degradation process. Recently, as a novel method for blind source separation based on high statistics, Independent Component Analysis (ICA)'s computation algorithms and applications are widely studied. In this paper, we present a Non-negative ICA algorithm which is used to the blind image restoration with the constraint of non-negativity. Besides this, through a matrix of de-correlation, it can reduce the requirements to the independence of the source signals in ICA algorithm. Through some computer simulation and experiments for real images, we show the effectiveness of the presented method.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Sanfeng Li, Shijie Wang, Limin Luo, "Study of blind image restoration algorithm based on non-negative independent component analysis", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749544 (30 October 2009); doi: 10.1117/12.831426; https://doi.org/10.1117/12.831426
PROCEEDINGS
6 PAGES


SHARE
Back to Top