PCNNP: a pulse-coupled neural network processor

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