Memristive continuous Hopfield neural network circuit for image restoration

  • Qinghui Hong
  • Ya Li
  • Xiaoping WangEmail author
Original Article


Image restoration (IR) methods based on neural network algorithms have shown great success. However, the hardware circuits that can perform real-time IR task with high-effective analog computation are few in the literature. To address such problem, we propose a memristor-based continuous Hopfield neural network (HNN) circuit for processing the IR task in this work. In our circuit, a single memristor crossbar array is used to represent synaptic weights and perform matrix operations. Current feedback operation amplifiers are utilized to achieve integral operation and output function. Given these designs, the proposed circuit can perform continuous recursive operations in parallel and process different optimization problems with the programmability of the memristor array. On the basis of the proposed circuit, binary and greyscale image restorations are conducted through self-organizing network operations, providing a hardware implementation platform for IR tasks. Comparative simulations show the designed HNN circuit provides effective improvements in terms of speed and accuracy compared with software simulation. Moreover, the hardware circuit shows good robustness to memristive variation and input noise.


Memristor Circuit design Hopfield neural network Image restoration 



This work was supported by the National Natural Science Foundation of China under Grant 61876209 and the National Key R&D Program of China under Grant 2017YFC1501301.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Akbarizadeh G, Tirandaz Z, Kooshesh M (2014) A new curvelet-based texture classification approach for land cover recognition of sar satellite images. Malays J Comput Sci 27(3):218–239Google Scholar
  2. 2.
    Akbarizadeh G, Rangzan K, Kabolizadeh M et al (2016) Effective supervised multiple-feature learning for fused radar and optical data classification. IET Radar Sonar Navig 11(5):768–777Google Scholar
  3. 3.
    Akbarizadeh G (2012) A new statistical-based kurtosis wavelet energy feature for texture recognition of sar images. IEEE Trans Geosci Remote Sens 50(11):4358–4368CrossRefGoogle Scholar
  4. 4.
    Aswathi V, Mathew J (2015) A review on image restoration in medical images. Compusoft 4(4):1588Google Scholar
  5. 5.
    Bae W, Yoo J, Chul Ye J (2017) Beyond deep residual learning for image restoration: persistent homology-guided manifold simplification. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 145–153Google Scholar
  6. 6.
    Banham MR, Katsaggelos AK (1997) Digital image restoration. IEEE Signal Process Mag 14(2):24–41CrossRefGoogle Scholar
  7. 7.
    Baselice F, Ferraioli G, Ambrosanio M, Pascazio V, Schirinzi G (2018) Enhanced Wiener filter for ultrasound image restoration. Comput Methods Programs Biomed 153:71–81CrossRefGoogle Scholar
  8. 8.
    Chang HH, Li CY, Gallogly AH (2018) Brain MR image restoration using an automatic trilateral filter with GPU-based acceleration. IEEE Trans Biomed Eng 65(2):400–413CrossRefGoogle Scholar
  9. 9.
    Chen L, Li C, Huang T, Chen Y, Wang X (2014) Memristor crossbar-based unsupervised image learning. Neural Comput Appl 25(2):393–400CrossRefGoogle Scholar
  10. 10.
    Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307CrossRefGoogle Scholar
  11. 11.
    Duan H, Wang X (2016) Echo state networks with orthogonal pigeon-inspired optimization for image restoration. IEEE Trans Neural Netw Learn Syst 27(11):2413–2425MathSciNetCrossRefGoogle Scholar
  12. 12.
    Duan S, Dong Z, Hu X, Wang L, Li H (2016) Small-world Hopfield neural networks with weight salience priority and memristor synapses for digit recognition. Neural Comput Appl 27(4):837–844CrossRefGoogle Scholar
  13. 13.
    Farbod M, Akbarizadeh G, Kosarian A, Rangzan K (2018) Optimized fuzzy cellular automata for synthetic aperture radar image edge detection. J Electron Imaging 27(1):013030CrossRefGoogle Scholar
  14. 14.
    Furber S, Temple S (2007) Neural systems engineering. J R Soc Interface 4(13):193CrossRefGoogle Scholar
  15. 15.
    Guan J, Song LM, Huo ZX (2016) Application of a multiscale maximum entropy image restoration algorithm to HXMT observations. Chin Phys C 40(8):086203CrossRefGoogle Scholar
  16. 16.
    Guo X, Merrikh-Bayat F, Gao L, Hoskins BD, Alibart F, Linares-Barranco B, Theogarajan L, Teuscher C, Strukov DB (2015) Modeling and experimental demonstration of a Hopfield network analog-to-digital converter with hybrid CMOS/memristor circuits. Front Neurosci 9:488CrossRefGoogle Scholar
  17. 17.
    Hu X, Duan S, Wang L, Liao X (2011) Memristive crossbar array with applications in image processing. Sci Sin Inf 41(4):500–512CrossRefGoogle Scholar
  18. 18.
    Hu S, Liu Y, Liu Z, Chen T, Wang J, Yu Q, Deng L, Yin Y, Hosaka S (2015) Associative memory realized by a reconfigurable memristive Hopfield neural network. Nat Commun 6:7522CrossRefGoogle Scholar
  19. 19.
    Jin KH, McCann MT, Froustey E, Unser M (2017) Deep convolutional neural network for inverse problems in imaging. IEEE Trans Image Process 26(9):4509–4522MathSciNetzbMATHCrossRefGoogle Scholar
  20. 20.
    Li F, Su L, Jiang Y, Sun M (2013) A hybrid restoration approach of defocused image using MGAM and inverse filtering. Int J Image Graph Signal Process 5(8):22–28CrossRefGoogle Scholar
  21. 21.
    Li Y, Zhong Y, Xu L, Zhang J, Xu X, Sun H, Miao X (2013) Ultrafast synaptic events in a chalcogenide memristor. Sci Rep 3(4):1619CrossRefGoogle Scholar
  22. 22.
    Li Y, Zhong Y, Zhang J, Xu L, Wang Q, Sun H, Tong H, Cheng X, Miao X (2014) Activity-dependent synaptic plasticity of a chalcogenide electronic synapse for neuromorphic systems. Sci Rep 4(6184):4906Google Scholar
  23. 23.
    Li C, Hu M, Li Y, Jiang H, Ge N, Montgomery E, Zhang J, Song W, Dávila N, Graves CE et al (2018) Analogue signal and image processing with large memristor crossbars. Nat Electron 1(1):52CrossRefGoogle Scholar
  24. 24.
    Li T, Duan S, Liu J, Wang L (2018) An improved design of rbf neural network control algorithm based on spintronic memristor crossbar array. Neural Comput Appl 30(6):1939–1946CrossRefGoogle Scholar
  25. 25.
    Lim B, Son S, Kim H, Nah S, Mu Lee K (2017) Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 136–144Google Scholar
  26. 26.
    Ling C, Li C, Huang T, Wen S, Chen Y (2015) Memristor crossbar array for image storing. In: International symposium on advances in neural networks-isnn, vol 2015, pp 166–173Google Scholar
  27. 27.
    Liu B, Chen Y, Wysocki B, Huang T (2015) Reconfigurable neuromorphic computing system with memristor-based synapse design. Neural Process Lett 41(2):1–9CrossRefGoogle Scholar
  28. 28.
    Ma W, Caí F, Du C, Jeong Y, Zidan M, Lu WD (2016) Device nonideality effects on image reconstruction using memristor arrays. In: 2016 IEEE international electron devices meeting (IEDM), IEEE, pp 16–7Google Scholar
  29. 29.
    Modava M, Akbarizadeh G, Soroosh M (2018) Integration of spectral histogram and level set for coastline detection in SAR images. IEEE Trans Aerosp Electron Syst 55(2):810–819CrossRefGoogle Scholar
  30. 30.
    Nie S, Zheng M, Ji Q (2018) The deep regression bayesian network and its applications: probabilistic deep learning for computer vision. IEEE Signal Process Mag 35(1):101–111CrossRefGoogle Scholar
  31. 31.
    Norouzi M, Akbarizadeh G, Eftekhar F (2018) A hybrid feature extraction method for SAR image registration. Signal Image Video Process 12(8):1559–1566CrossRefGoogle Scholar
  32. 32.
    Peng Y, Suo J, Dai Q, Xu W (2014) Reweighted low-rank matrix recovery and its application in image restoration. IEEE Trans Cybern 44(12):2418–2430CrossRefGoogle Scholar
  33. 33.
    Raeisi A, Akbarizadeh G, Mahmoudi A (2018) Combined method of an efficient cuckoo search algorithm and nonnegative matrix factorization of different zernike moment features for discrimination between oil spills and lookalikes in SAR images. IEEE J Sel Top Appl Earth Observ Remote Sens 99:1–13Google Scholar
  34. 34.
    Sharifzadeh F, Akbarizadeh G, Kavian YS (2018) Ship classification in SAR images using a new hybrid CNN–MLP classifier. J Indian Soc Remote Sens 6:1–12Google Scholar
  35. 35.
    Strukov DB, Snider GS, Stewart DR, Williams RS (2008) The missing memristor found. Nature 453(7191):80CrossRefGoogle Scholar
  36. 36.
    Sun Y, Zhang L, Teng F, Liu X (2017) Variational bayesian blind restoration reconstruction based on shear wave transform for low-dose medical CT image. EURASIP J Image Video Process 1:84CrossRefGoogle Scholar
  37. 37.
    Tai Y, Yang J, Liu X, Xu C (2017) Memnet: a persistent memory network for image restoration. In: Proceedings of the IEEE international conference on computer vision, pp 4539–4547Google Scholar
  38. 38.
    Takagi Y, Fujisawa T, Ikehara M (2017) Image restoration of JPEG encoded images via block matching and Wiener filtering. IEICE Trans Fundam Electron Commun Comput Sci 100(9):1993–2000CrossRefGoogle Scholar
  39. 39.
    Yang J, Wang L, Wang Y, Guo T (2017) A novel memristive Hopfield neural network with application in associative memory. Neurocomputing 227:142–148CrossRefGoogle Scholar
  40. 40.
    Yong X, Jie W, Fei L, Zheng Z (2017) Review of video and image defogging algorithms and related studies on image restoration and enhancement. IEEE Access 4:165–188Google Scholar
  41. 41.
    Yuan Q, Zhang Q, Li J, Shen H, Zhang L (2018) Hyperspectral image denoising employing a spatial–spectral deep residual convolutional neural network. IEEE Trans Geosci Remote Sens 99:1–14Google Scholar
  42. 42.
    Zeng X, Wen S, Zeng Z, Huang T (2018) Design of memristor-based image convolution calculation in convolutional neural network. Neural Comput Appl 30(2):503–508CrossRefGoogle Scholar
  43. 43.
    Zhang K, Zuo W, Gu S, Zhang L (2017) Learning deep CNN denoiser prior for image restoration. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3929–3938Google Scholar
  44. 44.
    Zhang Y, Wang X, Li Y, Friedman EG (2017) Memristive model for synaptic circuits. IEEE Trans Circuits Syst II Express Briefs 64(7):767–771CrossRefGoogle Scholar
  45. 45.
    Zhang Y, Sun L, Yan C, Ji X, Dai Q (2018) Adaptive residual networks for high-quality image restoration. IEEE Trans Image Process 27(7):3150–3163MathSciNetzbMATHCrossRefGoogle Scholar
  46. 46.
    Zhou YT, Chellappa R, Vaid A, Jenkins BK (1988) Image restoration using a neural network. IEEE Trans Acoust Speech Signal Process 36(7):1141–1151zbMATHCrossRefGoogle Scholar
  47. 47.
    Zhou D (2015) Image restoration technology based on discrete neural network. In: MATEC web of conferences, EDP sciences, vol 25, p 03017Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina
  2. 2.Key Laboratory of Image Processing and Intelligent Control of Education Ministry of ChinaWuhanChina

Personalised recommendations