Abstract

To overcome the shortcomings of traditional image restoration model and total variation image restoration model, we propose a novel Hopfield neural network-based image restoration algorithm with adaptive mixed-norm regularization. The new error function of image restoration combines the L2-norm and L1-norm regularization types. A method of calculating the adaptive scale control parameter is introduced. Experimental results demonstrate that the proposed algorithm is better than other algorithms with single norm regularization in the improvement of signal-to-noise ratio (ISNR) and vision effect.

© 2009 Chinese Optics Letters

Selection of regularization parameter in total variation image restoration

Haiyong Liao, Fang Li, and Michael K. Ng
J. Opt. Soc. Am. A 26(11) 2311-2320 (2009)

Restoration of bandlimited images by an iterative damped least-squares method with adaptive regularization

Junji Maeda
Appl. Opt. 24(10) 1421-1425 (1985)

Photonic Hopfield neural network for the Ising problem

ZeYang Fan, JunMin Lin, Jian Dai, Tian Zhang, and Kun Xu
Opt. Express 31(13) 21340-21350 (2023)

Associative-memory model based on neural networks: modification of Hopfield model

Sang-Hoon Oh, Tae-Hoon Yoon, and Jae Chang Kim
Opt. Lett. 13(1) 74-76 (1988)

Optical implementation of the Hopfield neural network with matrix gratings

Sheng L. Yeh, Rong C. Lo, and Cha Y. Shi
Appl. Opt. 43(4) 858-865 (2004)