Abstract
Due to the effections of environment and human factor, images always contains degradation phenomenon caused by image blur and noise which reduces the image quality. So, focus on the topic of the improvement of image, this dissertation pays much attention on the study of image degradation model, image restoration and evaluation method. Firstly, the image degradation model is given. Then, a few evaluation algorithms of restoration are given. At last, three Hopfield Neural Network restoration algorithm based on Laplace operator, sub-optimal algorithm and Harmonic Model are investigated. Simulation results validate the efficiency of the algorithms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wu Y (2003) Research on image recovery algorithm. University of Electronic Science and Technology
Banham MR, Katsaggelos AK (1997) Digital image restoration. IEEE Signal Process Mag 14(3):24–41
Zou MY (2001) Deconvolution and signal recovery. National Defense Industry Press, Beijing
Chen B (2008) Research on the theory and algorithm of adaptive optical image restoration. University of Information Engineering
Zhou YT, Chellappa R, Vaid A et al (1988) Image restoration using a neural network. IEEE Trans Acoust Speech Sign Process 36(7):1141–1151
Paik JK, Katsaggelos AK (1990) Image restoration using the Hopfield network with nonzero autoconnection. Acoust Speech Sign Process 4:1909–1912
Paik JK, Katsaggelos AK (1992) Image restoration using a modified Hopfield Network. IEEE Trans Image Process 1(1):49–63
Paik JK, Katsaggelos AK (1990) Parallel and distributed image restoration using a modified Hopfield network. Parall Arch Image Process 298–307
Sun Y (2000a) Hopfield neural network based algorithms for image restoration and reconstruction. I. Algorithms and simulations. Sign Process 2105–2118
Sun Y (2000b) Hopfield neural network based algorithms for image restoration and reconstruction. II. Performance analysis. Sign Process 2119–2131
Sun Y, Li J, Yu S (1995) Improvement on performance of modified Hopfield neural network for image restoration. Image Process Patt Recogn 688–692
Wang L, Qi F, Mo Y (1997) Theoretical and experimental analyses of restoring degraded images based on continuous Hopfield neural networks. Neur Netw 3:1634–1637
Han Y, Lenan W (2004) Image restoration using a modified Hopfield neural network of continuous state change. Sign Process 20(5):431–435
Perry SW, Guan L (1998) A statistics-based weight assignment in a Hopfield neural network for adaptive image restoration. Neur Netw Proc 2:922–927
Yang HC, Wilson R (1995) Adaptive image restoration using a multiresolution Hopfield neural network. Image Process Appl 1995:198–202
Ghennam S, Benmahammed K (2001) Adaptive image restoration using Hopfield neural network. Neur Netw Sign Process 569–578
Wei Q, Huaidong L, Maria K et al (1998) Adaptive neural network for nuclear medicine image restoration. J VLSI Sign Process 18(3):297–315
Wong HS, Guan L (1997) Adaptive regularization in image restoration using a model-based neural network. Opt Eng 36(12):125–136
Muneyasu M, Yamamoto K, Hinamoto T (1995) Image restoration using layered neural networks and Hopfield networks. Image Process 33–36
Bilal M, Sharif M, Arfan Jaffar M et al (2010) Image restoration using modified Hopfield fuzzy regularization method. Fut Inform Technol 758–763
Yu S, Medvedev S, Jaime R (2000) Sensor and method fusion in remote sensing imagery with neural networks. Ant Prop Soc Int Symp 4:1960–1963
Perry SW, Guan L (2000) Weight assignment for adaptive image restoration by neural networks. Neur Netw 156–170
Liu P, Zhang Y, Mao ZG (2006) Adaptive neural network image restoration algorithm based on symbiotic matrix analysis. J Comp Aid Des Graph 18(8):1205–1211
Wu Y, Zhang H (2006) A novel image restoration algorithm using neural network based on variational PDE model. Commun Circ Syst Proc 433–436
Zhang HY, Sun Y, Wu YD (2008) The diffusion performance analysis of variational PDE based neural network restoration models. Commun Circ Syst 834–837
Wu YD, Sun Y, Zhang HY et al (2007) Variational PDE based image restoration using neural network. Image Process 85–93
Wu Y, Zhang H, Sun Y et al (2010) A parallel image restoration algorithm based on Harmonic model using neural networks. Ubi-media Comput 30–33
Wu YD, Sun SX (2007) Fast neural network image recovery algorithm based on reconciliation model. Comp Appl Res 24(6):158–160
Sun J, Zongben X (2006) An edge preserving regularization model for image restoration based on Hopfield neural network. Lect Notes Comput Sci 3972(1):563–568
Zhang H, Yadong W, Peng Q (2005) Image restoration using Hopfield neural network based on total variational model. Lect Notes Comput Sci 3497(1):735–740
Lou S, Ding ZL, Yuan F et al (2009) Application of Hopfield neural network and wavelet domain hidden Markov tree model for image recovery. Opt Precis Eng 17(11):2828–2834
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Jiang, M., Guo, N., Wei, Q., Chen, H. (2023). Neural Network Image Restoration Techniques. In: Chen, H., Liu, Z. (eds) Recent Advanced in Image Security Technologies. Studies in Computational Intelligence, vol 1079. Springer, Cham. https://doi.org/10.1007/978-3-031-22809-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-22809-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22808-7
Online ISBN: 978-3-031-22809-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)