Knowledge extraction from scenery images and recognition using fuzzy inference neural networks

Hitoshi Iyatomi, Masafumi Hagiwara

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A new method of extracting various types of human knowledge from scenery images in linguistic form and labeling the various regions of unknown images in an effective manner is proposed. In this system, partitioning of the input/output space can be performed in a self-organizing manner. Rule extraction is performed in parallel and automatically by using a knowledge extraction network (KEN). Depending on the type of image to be learned, two-phase processing including a self-organization phase and an LMS learning phase is performed by several KENs. The overall network output is then unified and knowledge extraction and region recognition are performed linguistically. Software that performs a series of such operations has been implemented and it has been confirmed that knowledge edge extraction and better image recognition can be performed linguistically even if human knowledge is not provided.

Original languageEnglish
Pages (from-to)82-90
Number of pages9
JournalElectronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)
Volume86
Issue number3
DOIs
Publication statusPublished - 2003 Mar

Fingerprint

data mining
Fuzzy inference
inference
Neural networks
linguistics
Image recognition
output
organizing
Linguistics
Labeling
learning
marking
computer programs
Processing

Keywords

  • Fuzzy inference
  • Image recognition
  • Knowledge extraction
  • Neural network
  • Scenery image

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{570a6630d9f34eb89c4767dcaaf69af7,
title = "Knowledge extraction from scenery images and recognition using fuzzy inference neural networks",
abstract = "A new method of extracting various types of human knowledge from scenery images in linguistic form and labeling the various regions of unknown images in an effective manner is proposed. In this system, partitioning of the input/output space can be performed in a self-organizing manner. Rule extraction is performed in parallel and automatically by using a knowledge extraction network (KEN). Depending on the type of image to be learned, two-phase processing including a self-organization phase and an LMS learning phase is performed by several KENs. The overall network output is then unified and knowledge extraction and region recognition are performed linguistically. Software that performs a series of such operations has been implemented and it has been confirmed that knowledge edge extraction and better image recognition can be performed linguistically even if human knowledge is not provided.",
keywords = "Fuzzy inference, Image recognition, Knowledge extraction, Neural network, Scenery image",
author = "Hitoshi Iyatomi and Masafumi Hagiwara",
year = "2003",
month = "3",
doi = "10.1002/ecjb.10138",
language = "English",
volume = "86",
pages = "82--90",
journal = "Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)",
issn = "8756-663X",
publisher = "Scripta Technica",
number = "3",

}

TY - JOUR

T1 - Knowledge extraction from scenery images and recognition using fuzzy inference neural networks

AU - Iyatomi, Hitoshi

AU - Hagiwara, Masafumi

PY - 2003/3

Y1 - 2003/3

N2 - A new method of extracting various types of human knowledge from scenery images in linguistic form and labeling the various regions of unknown images in an effective manner is proposed. In this system, partitioning of the input/output space can be performed in a self-organizing manner. Rule extraction is performed in parallel and automatically by using a knowledge extraction network (KEN). Depending on the type of image to be learned, two-phase processing including a self-organization phase and an LMS learning phase is performed by several KENs. The overall network output is then unified and knowledge extraction and region recognition are performed linguistically. Software that performs a series of such operations has been implemented and it has been confirmed that knowledge edge extraction and better image recognition can be performed linguistically even if human knowledge is not provided.

AB - A new method of extracting various types of human knowledge from scenery images in linguistic form and labeling the various regions of unknown images in an effective manner is proposed. In this system, partitioning of the input/output space can be performed in a self-organizing manner. Rule extraction is performed in parallel and automatically by using a knowledge extraction network (KEN). Depending on the type of image to be learned, two-phase processing including a self-organization phase and an LMS learning phase is performed by several KENs. The overall network output is then unified and knowledge extraction and region recognition are performed linguistically. Software that performs a series of such operations has been implemented and it has been confirmed that knowledge edge extraction and better image recognition can be performed linguistically even if human knowledge is not provided.

KW - Fuzzy inference

KW - Image recognition

KW - Knowledge extraction

KW - Neural network

KW - Scenery image

UR - http://www.scopus.com/inward/record.url?scp=0037333984&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037333984&partnerID=8YFLogxK

U2 - 10.1002/ecjb.10138

DO - 10.1002/ecjb.10138

M3 - Article

AN - SCOPUS:0037333984

VL - 86

SP - 82

EP - 90

JO - Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)

JF - Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)

SN - 8756-663X

IS - 3

ER -