Recognition of scenery images considering positional relation using fuzzy inference neural networks

Atsushi Yamamura; Masafumi Hagiwara

Recognition of scenery images considering positional relation using fuzzy inference neural networks

Department of Information and Computer Science

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this paper, we propose a new system for recognition of scenery images by learning. The proposed system consists of 2 parts. One is the part which infers based on absolute position of target. The other is the part which infers based on relative position of target. Each part consists of Fuzzy Interference Neural Network (FINN) [6] which can extract fuzzy if-then rules automatically. So the system can extract knowledge about absolute position and relative position. Through computer experiments, it can be seen that the proposed system can recognize the image much correctly.

Original language	English
Pages (from-to)	1205-1210
Number of pages	6
Journal	Proceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume	2
Publication status	Published - 2001 Dec 1
Event	2001 IEEE International Conference on Systems, Man and Cybernetics - Tucson, AZ, United States Duration: 2001 Oct 7 → 2001 Oct 10

Keywords

Fuzzy
Image recognition
Neural network
Rule extraction

ASJC Scopus subject areas

Control and Systems Engineering
Hardware and Architecture

Cite this

@article{23920ef654f145b79d0e774743030783,

title = "Recognition of scenery images considering positional relation using fuzzy inference neural networks",

abstract = "In this paper, we propose a new system for recognition of scenery images by learning. The proposed system consists of 2 parts. One is the part which infers based on absolute position of target. The other is the part which infers based on relative position of target. Each part consists of Fuzzy Interference Neural Network (FINN) [6] which can extract fuzzy if-then rules automatically. So the system can extract knowledge about absolute position and relative position. Through computer experiments, it can be seen that the proposed system can recognize the image much correctly.",

keywords = "Fuzzy, Image recognition, Neural network, Rule extraction",

author = "Atsushi Yamamura and Masafumi Hagiwara",

year = "2001",

month = dec,

day = "1",

language = "English",

volume = "2",

pages = "1205--1210",

journal = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",

issn = "0884-3627",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2001 IEEE International Conference on Systems, Man and Cybernetics ; Conference date: 07-10-2001 Through 10-10-2001",

}

TY - JOUR

T1 - Recognition of scenery images considering positional relation using fuzzy inference neural networks

AU - Yamamura, Atsushi

AU - Hagiwara, Masafumi

PY - 2001/12/1

Y1 - 2001/12/1

N2 - In this paper, we propose a new system for recognition of scenery images by learning. The proposed system consists of 2 parts. One is the part which infers based on absolute position of target. The other is the part which infers based on relative position of target. Each part consists of Fuzzy Interference Neural Network (FINN) [6] which can extract fuzzy if-then rules automatically. So the system can extract knowledge about absolute position and relative position. Through computer experiments, it can be seen that the proposed system can recognize the image much correctly.

AB - In this paper, we propose a new system for recognition of scenery images by learning. The proposed system consists of 2 parts. One is the part which infers based on absolute position of target. The other is the part which infers based on relative position of target. Each part consists of Fuzzy Interference Neural Network (FINN) [6] which can extract fuzzy if-then rules automatically. So the system can extract knowledge about absolute position and relative position. Through computer experiments, it can be seen that the proposed system can recognize the image much correctly.

KW - Fuzzy

KW - Image recognition

KW - Neural network

KW - Rule extraction

UR - http://www.scopus.com/inward/record.url?scp=0035723681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035723681&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0035723681

SN - 0884-3627

VL - 2

SP - 1205

EP - 1210

JO - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

JF - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

T2 - 2001 IEEE International Conference on Systems, Man and Cybernetics

Y2 - 7 October 2001 through 10 October 2001

ER -

Recognition of scenery images considering positional relation using fuzzy inference neural networks

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this