Title :
A Novel Image Restoration Algorithm Using Neural Network Based on Variational PDE Model
Author :
Yadong, Wu ; Hongying, Zhang
Author_Institution :
Sch. of Comput. Sci. & Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu
Abstract :
The variational partial differential equation (PDE) model is introduced into image restoration framework using neural network. A novel image restoration algorithm based on harmonic diffusion equation is given. And, the convergence of this restored algorithm is also analyzed. The proposed algorithm could deblur the degraded image while preserve edges. Experimental results show that the presented algorithm is superior to the traditional restoration algorithm in preserving image edges, and has a better restoration effect
Keywords :
image restoration; neural nets; partial differential equations; harmonic diffusion equation; image deblurring; image edges preservation; image restoration algorithm; neural network; partial differential equation; variational PDE model; Algorithm design and analysis; Atmospheric modeling; Computer science; Convergence; Degradation; Hopfield neural networks; Image restoration; Laplace equations; Neural networks; Nonlinear equations;
Conference_Titel :
Communications, Circuits and Systems Proceedings, 2006 International Conference on
Conference_Location :
Guilin
Print_ISBN :
0-7803-9584-0
Electronic_ISBN :
0-7803-9585-9
DOI :
10.1109/ICCCAS.2006.284670
