An evaluation of the image recognition method using pulse coupled neural network

Authors:
Masato Yonekawa;Hiroaki Kurokawa
Affiliations:
School of Computer Science, Tokyo University of Technology, Hachioji, Tokyo, Japan;School of Computer Science, Tokyo University of Technology, Hachioji, Tokyo, Japan
Venue:
ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Year:
2011

Citing 7
Cited 1

Image Processing Using Pulse-Coupled Neural Networks

Image Processing Using Pulse-Coupled Neural Networks
Feature linking via synchronization among distributed assemblies: Simulations of results from cat visual cortex

Neural Computation
A Color Image Segmentation Using Inhibitory Connected Pulse Coupled Neural Network

Advances in Neuro-Information Processing
The parameter optimization of the pulse coupled neural network for the pattern recognition

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Object detection using unit-linking PCNN image icons

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
Neural mechanisms of scene segmentation: recordings from the visual cortex suggest basic circuits for linking field models

IEEE Transactions on Neural Networks
PCNN models and applications

IEEE Transactions on Neural Networks

The capacity and the versatility of the pulse coupled neural network in the image matching

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

A technique for the image recognition is major issue in the image processing and the image recognition method using pulse coupled neural network (PCNN) have been studied as one of the valid method. The most outstanding feature of the method using PCNN is that the method is valid for the rotation, magnification and shrinking of the image. Also, the good compatibility to the hardware implementation is significant feature of the PCNN. In our previous study, we proposed the GA based learning method for the PCNN parameters which enable the reliable results of image recognition. In this study, we evaluate the image recognition method using PCNN with our learning method. In the simulation results, we clarify the characteristics of recognition rate to the number of the images to be learned using our proposed learning method.