Skip to main content
SpringerLink
Log in

Pulse-coupled neural networks and parameter optimization methods

  • Review
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

In this paper, a review of parameter optimization methods of pulse-coupled neural networks (PCNNs) is presented. Considering that PCNN has been used in image processing for many years, the aim of this paper was to provide an overview of the work that has been done and to serve as a useful reference for those who are looking for PCNN parameter optimization methods and those who are researching PCNN applications for a specific field. This paper first briefly reviews the PCNN model, including the standard PCNN and several variants of PCNN. Then, we emphasize the optimization methods for PCNN’s parameters, describing three types of parameter optimization methods in detail. Next, the paper summarizes the applications of the optimized models of PCNN with adaptive parameters in image segmentation, image fusion, image denoising and edge detection.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

References

  1. Eckhorn R, Reitboeck HJ, Arndt M, Dicke PW (1989) A neural network for feature linking via synchronous activity: results from cat visual cortex and from simulations. In: Cotterill RMJ (ed) Models of brain function. Cambridge University Press, Cambridge, pp 255–272

    Google Scholar 

  2. Johnson JL, Padgett ML (1999) PCNN models and applications. IEEE Trans Neural Netw 10(3):480–498

    Article  Google Scholar 

  3. Ranganath HS, Kuntimad G, Johnson JL (1995) Pulse coupled neural networks for image processing. In: Proceedings IEEE Southeastcon ‘95. Visualize the future, pp 37–43

  4. Qi YF, Huo YL, Zhang JS (2008) A automatic image segmentation method based on simplified PCNN and minimum scatter within clusters. J Optoelectron Laser 19(9):1258–1264

    Google Scholar 

  5. Deng LB (2008) Image segmentation method based on PCNN and two-dimension MCC. J Proj Rockets Missiles Guid 28(3):237–239

    Google Scholar 

  6. Ma YD, Zhan K, Wang ZB (2010) Applications of pulse-coupled neural networks. Higher Education Press, Beijing, pp 1–199

    Book  MATH  Google Scholar 

  7. Zhou D, Gao C, Guo YC (2014) A coarse-to-fine strategy for iterative segmentation using simplified pulse-coupled neural network. Soft Comput 18(3):557–570

    Article  Google Scholar 

  8. Gao C, Zhou D, Guo Y (2013) Automatic iterative algorithm for image segmentation using a modified pulse-coupled neural network. Neurocomputing 119:332–338

    Article  Google Scholar 

  9. Zhang BH, Zhang CT, Wu JS, Liu HL (2014) A medical image fusion method based on energy classification of BEMD components. Opt-Int J Light Electron Opt 125(1):146–153

    Article  Google Scholar 

  10. Zhang D, Nishimura TH (2010) Pulse coupled neural network based anisotropic diffusion method for 1/f noise reduction. Math Comput Model 52(11):2085–2096

    Article  Google Scholar 

  11. He K, Li SF, Wang C(2010) Modified PCNN model and its application to mixed-noise removal. In: 2010 International conference on and information technology & ocean engineering innovative computing & communication, 2010 Asia-Pacific conference on (CICC-ITOE), pp 213–216

  12. Ebied HM, Revett K, Tolba MF (2013) Evaluation of unsupervised feature extraction neural networks for face recognition. Neural Comput Appl 22(6):1211–1222

    Article  Google Scholar 

  13. Hou YM, Rao NN, Lun XM, Liu F (2014) Gait object extraction and recognition in dynamic and complex scene using pulse coupled neural network and feature fusion. J Med Imaging Health Inform 4(2):325–330

    Article  Google Scholar 

  14. Shi Z, Hu JL (2010) Image edge detection method based on a simplified PCNN model with anisotropic linking mechanism. In: 10th International conference on intelligent systems design and applications (ISDA), pp 330–335

  15. Hu JL (2013) A modified pulse coupled neural network with anisotropic synaptic weight matrix for image edge detection. IEICE Trans Fundam Electron Commun Comput Sci 96(6):1460–1467

    Google Scholar 

  16. Yuan HZ, Hou JF, Li Y (2009) Pulse coupled neural network algorithm for object detection in infrared image. In: Proceedings of the 2009 international symposium on computer network and multimedia technology (CNMT 2009), pp 1–4

  17. Qu H, Yi Z, Yang SX (2013) Efficient shortest-path-tree computation in network routing based on pulse-coupled neural networks. Cybernetics 43(3):995–1010

    Google Scholar 

  18. Xu DC, Li BL, Nijholt A (2009) A novel approach based on PCNNs template for fingerprint image thinning. In: 2009 8th IEEE/ACIS international conference on computer and information science (ICIS), pp 115–119

  19. Deco G, Schurmann B (1999) Spatiotemporal coding in the cortex: information flow-based learning in spiking neural networks. Neural Comput 11(4):919–934

    Article  Google Scholar 

  20. Burkitt AN, Clark GM (1999) New technique for analyzing integrate and fire neurons[J]. Neurocomputing 26:93–99

    Article  MATH  Google Scholar 

  21. Ekblad U, Kinser JM, Atmera J, Zetterlunda N (2004) The intersecting cortica model in image processing. Nucl Instrum Methods Phys Res A 525(1):392–396

    Article  Google Scholar 

  22. Gu XD (2004) Equivalence relation between PCNN and mathematical morphology in image processing. J Comput Aided Des Comput Graph 16(8):1029–1032

    Google Scholar 

  23. Ma YD, Dai RL, Li L (2002) Automated image segmentation using pulse coupled neural networks and image’s entropy. J China Inst Commun 23(1):46–51

    Google Scholar 

  24. Kuntimad G, Ranganath HS (1999) Perfect image segmentation using pulse coupled neural networks. IEEE Trans Neural Netw 10(3):591–598

    Article  Google Scholar 

  25. Eckhorn R, Reitboeck HJ, Arndt M, Dicke P (1990) Feature linking via synchronization among distributed assemblies: simulations of results from cat visual cortex. Neural Comput 2(3):293–307

    Article  Google Scholar 

  26. Zheng QQ, Shu ZB (2013) A new approach for automated image segmentation based on simplified PCNN. Comput Aided Draft Design Manuf 23(1):21–26

    Google Scholar 

  27. Wang XF, Li BN, Huang YL, Wang XR (2011) Feature extraction from noisy image using intersecting cortical model. Appl Mech Mater 40:516–522

    Article  Google Scholar 

  28. Kavitha CT, Chellamuthu C, Rajesh R (2012) Multimodal medical image fusion using discrete ripplet transform and intersecting Cortical Model. Procedia Eng 38:1409–1414

    Article  Google Scholar 

  29. Mokhayeri F, Akbarzadeh-T MR (2011) A novel facial feature extraction method based on ICM network for affective recognition. In: The 2011 international joint conference on neural networks (IJCNN). IEEE, pp 1988–1993

  30. Wang RH, Song JS, Zhang XM (2012) SAR image classification in urban areas using Unit-Linking pulse coupled neural network. Adv Multimed Softw Eng Comput 1:39–44

    Google Scholar 

  31. Gu XD (2008) Feature extraction using unit-linking pulse coupled neural network and its applications. Neural Process Lett 27(1):25–41

    Article  Google Scholar 

  32. Li HY, Xu D, Zong R (2009) Face recognition based on unit-linking PCNN time signature. In: International conference on advanced computer control, 2009. ICACC’09. IEEE, pp 360–364

  33. Zong R, Li H, Xu D (2009) Face recognition based on Gabor features and unit-linking PCNN. In: 2nd International congress on image and signal processing, 2009, CISP’09. IEEE, pp 1–5

  34. Cui KB, Li BS, Yuan JS, Wang P (2014) An improved Unit-Linking PCNN for segmentation of infrared insulator image. Appl Math 8(6):2997–3004

    Google Scholar 

  35. Liu Q, Yang XP, Ma XS (2013) The multi-valued astronomical image segmentation based on pulse coupled neural networks. In: 2013 Fourth international conference on intelligent systems design and engineering applications, IEEE, pp 72–675

  36. Yamada H, Ogawa Y, Ishimura K, Wada M (2003) Face detection using pulse-coupled neural network. In: Proceedings of 2003 SICE annual conference, vol 3. IEEE, Fukui, pp 2784–2788

  37. Kong WW, Lei YJ, Lei Y, Lu S (2011) Image fusion technique based on non-subsampled contourlet transform and adaptive unit-fast-linking pulse-coupled neural network. IET Image Proc 5(2):113–121

    Article  Google Scholar 

  38. Wang ZB, Ma YD (2008) Medical image fusion using m-PCNN. Int J Multi-Sens Multi-Sour Inf Fusion 9(2):176–185

    Google Scholar 

  39. Wang ZB, Ma YD (2007) Dual-channel PCNN and its application in the field of image fusion. In: Proceedings of the 3rd international conference on natural computation, vol 1, pp 755–759

  40. Xiao ZH, Shi J, Chang Q (2009) Image segmentation with simplified PCNN. In: 2nd International congress on image and signal processing, CISP’09. IEEE, pp 1–4

  41. Tang N, Jiang GP, Lv QW (2012) Adaptive 3D image segmentation based on optimized PCNN. Appl Res Comput 29(4):1591–1594

    Google Scholar 

  42. Qu H, Yang SX, Willms AR, Yi Z (2009) Real-time robot path planning based on a modified pulse-coupled neural network model. Neural Netw IEEE Trans 20(11):1724–1739

    Article  Google Scholar 

  43. Chang Yao, Chen HJ, Li JP (2008) Analysis of dynamic behaviors of improved pulse coupled neural network in image processing. Acta Autom Sin 34(10):1291–1297

    MathSciNet  MATH  Google Scholar 

  44. Deng XY, Ma YD (2012) PCNN model automatic parameters determination and its modified model. Acta Electron Sin 40(5):955–964

    MathSciNet  Google Scholar 

  45. Deng XY, Ma YD (2014) PCNN model analysis and its automatic parameters determination in image segmentation and edge detection. Chin J Electron 23(1):97–103

    Google Scholar 

  46. Deng XY, Ma YD (2011) PCNN automatic parameters determination in image segmentation based on the analysis of neuron firing time. In: Proceedings of the sixth international conference on intelligent systems and knowledge engineering, pp 85–91

  47. Bi YW, Qiu TH, Li X, Guo Y (2004) Automatic image segmentation based on a simplified pulse coupled neural network. In: Lect. International symposium on neural networks. Proceedings, vol 2, pp 405–410

  48. Zhao ZJ, Zhao CH, Zhang ZH (2007) A new method of PCNN’s parameter’s optimization. Acta Electron Sin 35(5):996–1000

    Google Scholar 

  49. Yang YC, Dang JW, Wang YP (2012) A medical image fusion method based on lifting Wavelet transform and adaptive PCNN. J Comput-Aided Des Comput Graph 24(4):494–499

    Google Scholar 

  50. Li ML, Li YJ, Wang HM, Zhang K (2010) A new image fusion algorithm based on adaptive PCNN. J Optoelectron Laser 21(5):779–782

    Google Scholar 

  51. Yan CM, Guo BL, Yi M (2012) Multifocus image fusion method based on improved LP and adaptive PCNN. Control Decis 27(5):703–708

    MathSciNet  MATH  Google Scholar 

  52. Li HY, Zhang YF, Xu D (2010) Noise and speckle reduction in doppler blood flow spectrograms using an adaptive pulse-coupled neural network. Eurasip J Adv Signal Process 2010:1–11

    Article  Google Scholar 

  53. Fu JC, Chen CC, Chai JW, Wong STC, Li IC (2010) Image segmentation by EM-based adaptive pulse coupled neural networks in brain magnetic resonance imaging. Comput Med Imaging Graph 34(4):308–320

    Article  Google Scholar 

  54. Cao L, Tang N (2011) Fully automatic 3D algorithm of pulmonary parenchyma segmentation. Comput Eng Appl 47(22):137–140

    Google Scholar 

  55. Ni FY, Zhang Y (2011) Study of Face Image Segmentation Algorithm Based on PCNN. J Jiangsu Teach Univ Technol 17(4):10–20

    Google Scholar 

  56. Miao QG, Wang BS (2006) Novel algorithm of multi-focus image fusion using adaptive PCNN. Dianzi Yu Xinxi Xuebao. J Electron Inf Technol, 28(3):466–470

  57. Miao QG, Wang BS (2008) A novel image fusion algorithm based on local contrast and adaptive PCNN. Chin J Comput 31(5):875–880

    Article  Google Scholar 

  58. Chen YL, Park SK, Ma YD, Ala R (2011) A new automatic parameters setting method of a simplified PCNN for image segmentation. IEEE Trans Neural Netw 22(6):880–892

    Article  Google Scholar 

  59. Rava TH, Bettaiah V, Ranganath HS (2011) Adaptive pulse coupled neural network parameters for image segmentation. World Acad Sci Eng Technol 73:1046–1056

    Google Scholar 

  60. Zhou DG, Gao C, Guo YC (2013) Simplified pulse coupled neural network with adaptive multilevel threshold for infrared human image segmentation. J Comput-Aided Des Comput Graph 25(2):208–214

    Google Scholar 

  61. Shi H, Rong J, Zhou X (2015) A novel method for image segmentation using pulse-coupled neural network based on root mean square of gray scale. In: Wong WE (ed) Proceedings of the 4th international conference on computer engineering and networks. Springer, Cham, pp 695–704

    Chapter  Google Scholar 

  62. Ma YD, Qi CL (2006) Study of automated PCNN system based on genetic algorithm. J Syst Simul 18(3):722–725

    MathSciNet  Google Scholar 

  63. Qu S, Yang H (2015) Infrared image segmentation based on PCNN with genetic algorithm parameter optimization. Qiangjiguang Yu Lizishu/High Power Laser Part Beams, 27(5):1001–4322

  64. Mohammed MM, Badr A, Abdelhalim MB (2015) Image classification and retrieval using optimized Pulse-Coupled Neural Network. Expert Syst Appl 42(11):4927–4936

    Article  Google Scholar 

  65. Jiang XY (2012) A Self-adapting pulse-coupled neural network based on modified differential evolution algorithm and its application on image segmentation. Int J Digital Content Technol Appl 6(20):501–509

    Article  Google Scholar 

  66. Xu XZ, Ding SF, Zhao ZP, Zhu H (2011) Particle swarm optimization for automatic parameters determination of pulse coupled neural network. J Comput 6(8):1546–1553

    Google Scholar 

  67. Wang J, Cong F (2008) Grayscale image edge detection based on pulse-coupled neural network and particle swarm optimization. In: 2008 Chinese control and decision conference (CCDC), pp 2576–2579

  68. Hage IS, Hamade RF (2013) Segmentation of histology slides of cortical bone using pulse coupled neural networks optimized by particle-swarm optimization. Comput Med Imaging Graph 37(7–8):466–474

    Article  Google Scholar 

  69. Xu XZ, Ding SF, Shi ZZ, Zhu H, Zhao ZP (2012) A self-adaptive method for optimization the parameters of pulse coupled neural network based QPSO algorithm. Pattern Recognit Artif Intell 25(6):909–915

    Google Scholar 

  70. Liao YP, Zhang P, Guo Q, Wan J (2014) PCNN document segmentation method based on bacterial foraging optimization algorithm. In: Sixth international conference on digital image processing. International society for optics and photonics, vol 9159, pp 91591T–91591T-7

  71. Gao KH, Duan HB, Xu Y, Zhang Y, Li ZS (2012) Artificial bee colony approach to parameters optimization of pulse coupled neural networks. In: 2012 10th IEEE international conference on industrial informatics (INDIN), IEEE, pp 128–132

  72. Mu LL, Zhao MZ, Zhang CZ (2013) Quantum particle swarm optimisation based on chaotic mutation for automatic parameters determination of pulse coupled neural network. Int J Comput Sci Math 4(4):354–362

    Article  MathSciNet  Google Scholar 

  73. Wu J, Liu YW et al (2015) Image retrieval combining FOA optimized PCNN and phase congruency. J Comput Aided Des Comput Graph 27(8):1483–1489

    Google Scholar 

  74. Wang ZB, Ma YD, Cheng FY (2010) R. Image Vis Comput 28(1):5–13

    Article  Google Scholar 

  75. Subashini MM, Sahoo SK (2014) Pulse coupled neural networks and its applications. Expert Syst Appl 41(8):3965–3974

    Article  Google Scholar 

  76. Xiao, ZH, Shi J, Chang Q (2009) Automatic image segmentation algorithm based on PCNN and fuzzy mutual information. In: Proceedings of the 2009 Ninth IEEE international conference on computer and information technology, vol 1, pp 241–245

  77. Zheng X, Peng ZM (2013) Image segmentation based on activity degree with pulse coupled neural networks. Opt Precis Eng 21(3):821–827

    Article  Google Scholar 

  78. Wang HQ, Ji CY, Gu BX, Tian GZ (2013) Cucumber image segmentation based on weighted connection coefficient pulse coupled neural network. Nongye Jixie Xuebao (Trans Chin Soc Agric Mach), 44(3):204–208

  79. Zhao YM (2013) The PCNN adaptive segmentation algorithm based on visual perception. In: Proceedings of the SPIE-the international society for optical engineering, vol 8761, pp 87611A–876116

  80. Wen CJ, Yu HL, He SS (2013) An image segmentation algorithm of corn disease based on the modified bionic pulse coupled neural network. In: 2013 Fourth global congress on intelligent systems (GCIS), IEEE, pp 99–101

  81. Yonekawa M, Kurokawa H (2009) An automatic parameter adjustment method of pulse coupled neural network for image segmentation. In: Artificial neural networks–ICANN 2009. Springer, Berlin, pp 834–843

  82. Xia JX, Duan XH, Wei SC (2011) Application of adaptive PCNN based on neighborhood to medical image fusion. Appl Res Comput 28(10):3929–3933

    Google Scholar 

  83. Wang MH (2012) An improved algorithm for medical image fusion based on pulse coupled neural networks. Adv Mater Res 340:492–497

    Article  Google Scholar 

  84. Li Y, Wu XJ (2014) A novel image fusion method using self-adaptive dual-channel pulse coupled neural networks based on PSO evolutionary learning. Acta Electron Sin 42(2):217–222

    Google Scholar 

  85. Jiao ZQ, Xiong WL, Xu BG (2010) Image fusion using self-constraint pulse-coupled neural network. In: Li K, Jia L, Sun X, Fei MR, Irwin GW (eds) Life system modeling and intelligent computing. Springer, Berlin, pp 626–634

    Chapter  Google Scholar 

  86. Kong WW, Liu JP (2013) Image processing technique for image fusion based on nonsubsampled shearlet transform and improved pulse-coupled neural network. Opt Eng 52(1):017001

    Article  Google Scholar 

  87. Jin X, Nie R, Zhou D et al (2016) Multifocus color image fusion based on NSST and PCNN[J]. J Sens 2016(2):1–12

    Article  Google Scholar 

  88. Zhao C, Shao G, Ma L et al (2014) Image fusion algorithm based on redundant-lifting NSWMDA and adaptive PCNN. Opt-Int J Light Electron Opt 125(20):6247–6255

    Article  Google Scholar 

  89. Li JF, Zou BJ, Liang YX et al (2011) Based on local mean and variance of adaptive pulse coupled neural network image fusion. Multimed Signal Process (CMSP) 2:180–183

    Google Scholar 

  90. Zhang D, Mabu S, Hirasawa K (2010) Noise reduction using genetic algorithm based PCNN method. Syst Man Cybern (SMC) 2010:2627–2633

    Google Scholar 

  91. Zhang D, Mabu S, Hirasawa K (2011) Image denoising using pulse coupled neural network with an adaptive Pareto genetic algorithm. IEEE Trans Electr Electron Eng 6(5):474–482

    Article  Google Scholar 

  92. Tu YQ, Li SF, Wang MQ (2008) Mixed-noise removal for color images using modified PCNN model. Intell Inf Technol Appl 3:347–351

    Google Scholar 

  93. Cheng FY, Wang ZB, Ma YD, Yang LZ, Gao QX (2009) A new approach for edge detection of color microscopic image using modified pulse coupled neural networks. In: 2009 3rd International conference on bioinformatics and biomedical engineering, pp 1–4

  94. Xu F, Shan DG, Yang HC (2010) Image edge detection based on improved PCNN. In: Information science and engineering (ICISE), pp 3757–3760

  95. Wang XC, Cheng M, Liu YM et al (2011) Edge detection of color image using Unit-Linking PCNN. Appl Mech Mater 55:1211–1217

    Article  Google Scholar 

  96. He CT, Wang WX (2010) A PCNN-based edge detection algorithm for rock fracture images. In: 2010 Symposium on photonics and optoelectronic, SOPO 2010—Proceedings, pp 1–4

Download references

Acknowledgments

This work is supported by the Fundamental Research Funds for the Central Universities (No. 2013QNA24) and the Basic Research Program (Natural Science Foundation) of Jiangsu Province of China (No. BK20130209).

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, People’s Republic of China

    Xinzheng Xu, Guanying Wang & Shifei Ding

  2. School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, People’s Republic of China

    Yuhu Cheng & Xuesong Wang

Authors
  1. Xinzheng Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guanying Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shifei Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuhu Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xuesong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xuesong Wang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, X., Wang, G., Ding, S. et al. Pulse-coupled neural networks and parameter optimization methods. Neural Comput & Applic 28 (Suppl 1), 671–681 (2017). https://doi.org/10.1007/s00521-016-2397-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-016-2397-2

Keywords

Search

Navigation