Presentation 2002/12/6
The application of MCP in the satellite image classification : Land cover classification of the LandSat image
Seitaro Kikuchi, Mitsuyoshi Tomiya,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) MCP(Modified Counter-Propagation) is the neural network which consists of 3 layers where neuron in rivalry layer of CP(Counter-Propagation) was expanded in SOM(Self-Organizing Maps). The purpose of the reserch is the classifies of LandSat image by using MCP. LandSat image data are inputted in the input layer of MCP, and the RGB value which represented each category is substituted in the output layer. MCP is compared with the case that a learning is done only with SOM which is a learning without a teacher-data. And it becomes possible that it is classified quantitatively.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Modified Counter Propagation / Self-Organizing Maps / category classifies / LandSat
Paper # NC2002-101
Date of Issue

Conference Information
Committee NC
Conference Date 2002/12/6(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The application of MCP in the satellite image classification : Land cover classification of the LandSat image
Sub Title (in English)
Keyword(1) Modified Counter Propagation
Keyword(2) Self-Organizing Maps
Keyword(3) category classifies
Keyword(4) LandSat
1st Author's Name Seitaro Kikuchi
1st Author's Affiliation Department of Applied Physics, Seikei University()
2nd Author's Name Mitsuyoshi Tomiya
2nd Author's Affiliation Department of Applied Physics, Seikei University
Date 2002/12/6
Paper # NC2002-101
Volume (vol) vol.102
Number (no) 508
Page pp.pp.-
#Pages 6
Date of Issue