15 November 2007 Algorithm for the blind deconvolution of images based on neural networks
Author Affiliations +
Proceedings Volume 6787, MIPPR 2007: Multispectral Image Processing; 67871B (2007) https://doi.org/10.1117/12.749379
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China
Abstract
An iterative blind deconvolution algorithm for degrade image is presented in this paper. The algorithm includes two steps, namely, the estimation of the point spread function of degrade image and the restoration using estimated point spread function. Two different Hopfield neural networks are built for realizing the two steps. An iterative procedure is used to control the restoration process. The simulation results indicate that the method is effective for blind deconvolution with high convergence speed.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Boxin Zuo, Jinwen Tian, Li Zu, Anhong Chen, "Algorithm for the blind deconvolution of images based on neural networks", Proc. SPIE 6787, MIPPR 2007: Multispectral Image Processing, 67871B (15 November 2007); doi: 10.1117/12.749379; https://doi.org/10.1117/12.749379
PROCEEDINGS
7 PAGES


SHARE
Back to Top