Title :
The diffusion performance analysis of variational PDE based neural network restoration models
Author :
Wu, Ya-Dong ; Sun, Yu ; Zhang, Hong-Ying
Author_Institution :
Coll. of Comput. Sci. & Technol., Southwest Univ. of Sci. & Technol., Mianyang
Abstract :
In this paper, we introduce two variational PDEs (Partial Differential Equations) as the regularization terms to the image restoration model based on the modified Hopfield neural network. The performance of these regularization terms is analyzed from the viewpoint of nonlinear diffusion. It can be shown that the two proposed restoration models have superior edge preserving performance than the traditional restoration model.
Keywords :
Hopfield neural nets; image restoration; partial differential equations; Hopfield neural network; diffusion performance analysis; image restoration model; neural network restoration models; partial differential equations; variational PDE; Atmospheric modeling; Computer science; Degradation; Educational institutions; Hopfield neural networks; Image restoration; Laplace equations; Neural networks; Partial differential equations; Performance analysis;
Conference_Titel :
Communications, Circuits and Systems, 2008. ICCCAS 2008. International Conference on
Conference_Location :
Fujian
Print_ISBN :
978-1-4244-2063-6
Electronic_ISBN :
978-1-4244-2064-3
DOI :
10.1109/ICCCAS.2008.4657899
