Presentation 2013-05-27
A study on the image feature extraction method by the IC-PCNN
Yuta ISHIDA, Hiroaki KUROKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The Pulse Coupled Neural Network(PCNN) is a neural network model that consists of spiking neurons. The PCNN has been applied to a lot of image processing, and the image matching is one of the successful application of the PCNN. In the image matching method using PCNN, the "PCNN Icon" that defined from the dynamics of the PCNN is used as a kind of the image feature value. This image matching technique is applied to a method for the content base image retrieval system. However, due to the structure of the PCNN, only the gray-scaled image is used in the PCNN, i.e., the color information of the image will be lost in the case of using color images. In this study, we propose the method of the image feature extraction using the Inhibitory connected PCNN(IC-PCNN) and applied to the image matching method. Where the IC-PCNN is an extended model of the PCNN for the color image processing without the loss of color information. We propose the method of using IC-PCNN. In the simulation, we show the results of the image matching using the color image database.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Inhibitory Connected Pulse Coupled Neural Network / Image matching
Paper # NLP2013-15
Date of Issue

Conference Information
Committee NLP
Conference Date 2013/5/20(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A study on the image feature extraction method by the IC-PCNN
Sub Title (in English)
Keyword(1) Inhibitory Connected Pulse Coupled Neural Network
Keyword(2) Image matching
1st Author's Name Yuta ISHIDA
1st Author's Affiliation Tokyo University of Technology()
2nd Author's Name Hiroaki KUROKAWA
2nd Author's Affiliation Tokyo University of Technology
Date 2013-05-27
Paper # NLP2013-15
Volume (vol) vol.113
Number (no) 69
Page pp.pp.-
#Pages 5
Date of Issue