Memristor-based multi-channel pulse coupled neural network for image fusion

doi:10.19682/j.cnki.1005-8885.2021.0046

中国邮电高校学报(英文) ›› 2020, Vol. 27 ›› Issue (6): 54-72.doi: 10.19682/j.cnki.1005-8885.2021.0046

• Image Processing • 上一篇下一篇

Memristor-based multi-channel pulse coupled neural network for image fusion

刘俭,吴成茂,田小平

西安邮电大学

收稿日期:2020-08-17 修回日期:2020-11-28 出版日期:2020-12-31 发布日期:2020-12-31
通讯作者: 刘俭 E-mail:13137739560@163.com
基金资助:
国家自然科学基金;陕西省自然科学基金

Memristor-based multi-channel pulse coupled neural network for image fusion

Liu Jian, Wu Chengmao, Tian Xiaoping

Received:2020-08-17 Revised:2020-11-28 Online:2020-12-31 Published:2020-12-31
Contact: liu jian E-mail:13137739560@163.com
Supported by:
The National Natural Science Foundation of China;the Shaanxi Natural Science Foundation of China

摘要/Abstract

摘要：

Image fusion is widely used in computer vision and image analysis. Considering that the traditional image fusion algorithm has a certain limitation in multi-channel image fusion, a memristor-based multi-channel pulse coupled neural network (M-MPCNN) for image fusion is proposed. Based on a dual-channel pulse coupled neural network (D-PCNN), a novel multi-channel pulse coupled neural network (M-PCNN) is firstly constructed in this paper. Then the exponential growth dynamic threshold model is used to improve the pulse generation of pulse coupled neural network, which can not only avoid multiple ignitions effectively, but can also improve operational efficiency and reduce complexity. At the same time, synchronous capture can also enhance image edge, which is more conducive to image fusion. Finally, the threshold and synaptic characteristics of pulse coupled neural networks (PCNNs) can be well realized by using a memristor-based pulse generator. Experimental results show that the proposed algorithm can fuse multi-source images more effectively than existing state-of-the-art fusion algorithms.

关键词: multi-channel, memristor, pulse coupled neural network

Abstract: Image fusion is widely used in computer vision and image analysis. Considering that the traditional image fusion algorithm has a certain limitation in multi-channel image fusion, a memristor-based multi-channel pulse coupled neural network (M-MPCNN) for image fusion is proposed. Based on a dual-channel pulse coupled neural network (D-PCNN), a novel multi-channel pulse coupled neural network (M-PCNN) is firstly constructed in this paper. Then the exponential growth dynamic threshold model is used to improve the pulse generation of pulse coupled neural network, which can not only avoid multiple ignitions effectively, but can also improve operational efficiency and reduce complexity. At the same time, synchronous capture can also enhance image edge, which is more conducive to image fusion. Finally, the threshold and synaptic characteristics of pulse coupled neural networks (PCNNs) can be well realized by using a memristor-based pulse generator. Experimental results show that the proposed algorithm can fuse multi-source images more effectively than existing state-of-the-art fusion algorithms.

Key words: multi-channel, memristor, pulse coupled neural network

Liu Jian, Wu Chengmao, Tian Xiaoping. Memristor-based multi-channel pulse coupled neural network for image fusion[J]. The Journal of China Universities of Posts and Telecommunications, 2020, 27(6): 54-72.

参考文献

1. Anderson C H. Filter-subtract-decimate hierarchical pyramid signal analyzing and synthesizing technique. USP 4718104, 1988-01-05.

2. Li M J, Dong Y B, Wang X L. Image fusion algorithm based on gradient pyramid and its performance evaluation. Applied Mechanics and Materials, 2014, 525: 715-718.

3. Mao R, Fu X S, Niu P J, et al. Multi-directional laplacian pyramid image fusion algorithm. Proceedings of the 3rd International Conference on Mechanical, Control and Computer Engineering (ICMCCE'18), 2018, Sept 14-16, Huhhot, China. Piscataway, NJ, USA: IEEE, 2018, 569-572.

4. Uniyal N, Verma S K. Image fusion using morphological pyramid consistency method. International Journal of Computer Applications. 2014, 95(25): 34-38.

5. Wang K P, Zheng M Y, Wei H Y, et al. Multi-modality medical image fusion using convolutional neural network and contrast pyramid. Sensors, 2020, 20(8): 124-127.

6. Parmar K, Kher R K, Thakkar F N. Analysis of CT and MRI image fusion using wavelet transform. Proceedings of th e 2012 International Conference on.Communication Systems and Network Technologies (CSNT'12), 2012, May 11-13, Rajkot, India. Piscataway, NJ, USA: IEEE, 2012: 4p.

7. Rockinger O. Image sequence fusion using a shift-invariant wavelet transform.Proceeding of the 1997 IEEE International Conference on Image Processing: Vol 3, 1997, Oct 26-29, Santa Barbara, CA, USA. Piscataway, NJ, USA: IEEE, 1997: 288-291.

8. Eckhorn R, Reitboeck H J, Arndt M, et al. Feature linking via synchronization among distributed assemblies: Simulations of results from cat visual cortex. Neural Computation, 1990, 2(3): 293-307.

9. Johnson J L, Padgett M L. PCNN models, and application. IEEE Trans on Neural Networks, 1999, 10(3): 480-498.

10. Ranganath H S, Kuntimad G, Johnson J L. Pulse coupled neural networks for image processing. Proceedings of the IEEE Southeastcon'95 Visualize the Future, 1995, Mar 26-29, Raleigh, NC, USA. Piscataway, NJ, USA: IEEE, 1995: 37-43.

11. Wang Z B, Ma Y D. Dual-channel PCNN and its application in the field of image fusion. Proceedings of the 3rd International Conference on Natural Computation (ICNC'07), 2007, Aug 24-27, Haikou, China. Piscataway, NJ, USA: IEEE, 2007.

12. Wang Z B, Ma Y D. Medical image fusion using m-PCNN. Information Fusion. 2008, 9(2): 176-185.

13. Fu C Y, Guo L. Hyperspectral image fusion based on wavelet transform and multi-channel pulse coupled neural network. Journal of Jilin University: Engineering and Technology Edition, 2011, 41(3): 838-843 (in Chinese)

14. Joglekar Y N, Wolf S J. The elusive memristor: Properties of basic electrical circuits. European Journal of Physics, 2009, 30(4): 661-675.

15. Shin, S, Kim K, Kang S M. Memristor applications for programmable analog ICs. IEEE Trans on Nanotechnology, 2011, 10(2): 266-274.

16. Hu X F, Duan S K, Wang L D, et al. Memristive crossbar array with applications in image processing. Science China: Information Sciences, 2012, 55(2): 461-472.

17. Dong Z K, Lai C S, Qi D L, et al. A general memristor-based pulse coupled neural network with variable linking coefficient for multi-focus image fusion. Neurocomputing, 2018, 308: 172-183.

18. Jo S H, Chang T, Ebong I, et al. Nanoscale memristor device as synapse in neuromorphic systems. Nano Letters, 2010, 10(4): 1297-1301.

19. Indiveri G, Linares-Barranco B, Legenstein R, et al. Integration of nanoscale memristor synapses in neuromorphic computing architectures. Nanotechnology, 2013, 24(38): Article 384010.

20. Xie X D, Wen S P, Zeng Z G, et al. Memristor-based circuit implementation of pulse-coupled neural network with dynamical threshold generators. Neurocomputing, 2018, 284: 10-16.

21. Zhu S, Wang L D, Duan S K, Memristive pulse coupled neural network with applications in medical image processing. Neurocomputing, 2017, 277: 149-157.

22. Chua L O, Memristor--The missing circuit element. IEEE Trans on Circuit Theory, 1971, 18(5): 507-519.

23. Strukov D B, Snider G S, Stewart D R, et al. The missing memristor found. Nature, 2008, 453(7191): 80-83.

24. Gale E. Uniform and piece-wise uniform fields in memristor models. Computer Science, arXiv:1404.5581, 2014.

25. Jaynes E T. Information theory and statistical mechanics. Physical Review Journals Archive, 1957, 106: 620-630.

26. Schönfeldt J C. Applications of the maximum entropy principle to time dependent processes. Master Thesis. Pretoria, South African: University of Pretoria, 2008.

27. Xydeas C S, Petrovic V. Objective image fusion performance measure. Electronics Letters, 2000, 36(4): 308-309.

28. Xiang T Z, Yan L, Gao R R. A fusion algorithm for infrared and visible images based on adaptive dual-channel unit-linking PCNN in NSCT domain. Infrared Physics & Technology, 2015, 69: 53-61.

29. Qu X B, Yan J W, Xiao H Z, et al. Image fusion algorithm based on spatial frequency excitation in non-downsampling contourlet domain. Acta Automatica Sinica, 2008, 34(12): 1508-1514.

Memristor-based multi-channel pulse coupled neural network for image fusion

Memristor-based multi-channel pulse coupled neural network for image fusion

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价