PCNNP: a pulse-coupled neural network processor

Author

Chacon MMI ; Zimmerman, Alejandro S. ; Sanchez, David A.

Author_Institution

DSP & Vision Lab., Chihuahua Inst. of Technol., Mexico

Volume

2

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

1581

Lastpage

1584

Abstract

Pulse-coupled neural networks, PCNN, have arisen as an alternative for image preprocessing. However, the PCNN model is a member of the artificial neural networks model and hence it inherits the problem of parameter specification. This paper presents a PCNN model that was generated by analysis of other PCNN models and describes what we call a PCNN processor, PCNNP. The PCNNP is a PCNN simulator with a user interface. The PCNN simulated in the PCNNP is a model generated from other PCNN models analysis. The PCNNP allows the user to analyze the behavior of the net by changing the linking and feeding kernels and the parameters of the neuron. The interface also incorporates different visualization tools to facilitate the analysis of the information generated by the net. The visualization modes have proved to be helpful to understand the internal activity of the PCNN and how this activity is modified by the parameters of the PCNN

Keywords

data visualisation; image processing equipment; neural chips; user interfaces; PCNN; PCNNP; artificial neural networks model; image preprocessing; image processing; parameter specification; pulse-coupled neural network processor; user interface; visualization tools; Analytical models; Artificial neural networks; Image processing; Information analysis; Joining processes; Kernel; Neural networks; Neurons; User interfaces; Visualization;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1007753

Filename

1007753