Skip to main content
Log in

An improved pulse coupled neural network for image processing

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

To develop new image processing applications for pulse coupled neural network (PCNN), this paper proposes an improved PCNN model by redesigning the linking input, activity strength, linking weight, pulse threshold and pixel update rule. Two typical image processing examples based on such a model, namely fingerprint orientation field estimation and noise removal, are presented for explaining how to use the PCNN and determine parameters in image processing. Experiments show that the improved model is quite useful, and the PCNN-based approaches achieve better image processing results than the traditional ones.

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

Access this article

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

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

    Article  Google Scholar 

  2. Ranganath HS, Kuntimad G, Johnson JL (1995) Pulse coupled neural networks for image processing. In: Proceedings of IEEE Southeastcon, Raleigh, NC, pp 37–43

  3. Johnson JL, Ritter D (1993) Observation of periodic waves in a pulse coupled neural network. Opt Lett 18:1253–1255

    Article  Google Scholar 

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

    Article  Google Scholar 

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

    Article  Google Scholar 

  6. Kinser JM (1999) Foveation by a pulse-coupled neural network. IEEE Trans Neural Netw 10(3):621–625

    Article  Google Scholar 

  7. Ranganath HS, Kuntimad G (1999) Object detection using pulse coupled neural network. IEEE Trans Neural Netw 10(3):615–620

    Article  Google Scholar 

  8. Gu X, Yu D, Zhang L (2004) Image thinning using pulse coupled neural network. Patt Recognit Lett 25:1075–1084

    Article  Google Scholar 

  9. Gu X, Yu D, Zhang L (2005) Image shadow removal using pulse coupled neural network. IEEE Trans Neural Netw 16(3):692–698

    Article  Google Scholar 

  10. Shang L, Yi Z, Ji L (2007) Binary image thinning using autowaves generated by PCNN. Neural Process Lett 25(1):49–62

    Article  Google Scholar 

  11. Shang L, Yi Z (2007) A class of binary images thinning using two PCNNs. Neurocomputing 70:1096–1101

    Google Scholar 

  12. Ji L, Yi Z, Pu X (2006) Fingerprint classification by SPCNN and combined LVQ networks. In: Proceedings of international conference on natural computation, Xi’an, China, LNCS4221, part I, pp 395–398

  13. Zhang J, Dong J, Shi M (2005) An adaptive method for image filtering with pulse-coupled neural networks. In: Proceedings of IEEE international conference on image processing, part 2, pp II-133–136.

  14. Cappelli R, Lumini A, Maio D, Maltoni D (1999) Fingerprint classification by directional image partitioning. IEEE Trans Patt Recognit Mach Intell 21(5):402–421

    Article  Google Scholar 

  15. Kulkarni JV, Patil BD, Holambe RS (2006) Orientation feature for fingerprint matching. Patt Recognit 39:1551–1554

    Article  MATH  Google Scholar 

  16. Nagaty KA (2003) On learning to estimate the block directional image of a fingerprint using a hierarchical neural network. Neural Netw 16:133–144

    Article  Google Scholar 

  17. Garnett R, Huegerich T, Chui C, He W (2005) A universal noise removal algorithm with an impulse detector. IEEE Trans Neural Netw 14(11):1747–1754

    Google Scholar 

  18. Naif A, Mohamed K, Ed J (2004) Detail preserving impulsive noise removal. Signal Process Image Commun 19:993–1003

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Luping Ji.

Additional information

This work was supported by National Science Foundation of China under Grant 60471055 and Specialized Research Fund for the Doctoral Program of Higher Education under Grant 20040614017.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ji, L., Yi, Z. & Shang, L. An improved pulse coupled neural network for image processing. Neural Comput & Applic 17, 255–263 (2008). https://doi.org/10.1007/s00521-007-0119-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-007-0119-5

Keywords

Navigation