Scenery image recognition and interpretation using fuzzy inference neural networks

Hitoshi Iyatomi, Masafumi Hagiwara

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

In this paper, we propose a new image recognition and interpretation system. The proposed system is composed of three processes: (1) regional segmentation process; (2) image recognition process; and (3) image interpretation process. As a pre-processing in the regional segmentation process, an input image is divided into some proper regions using techniques based on K-means algorithm. In both the image recognition and the interpretation processes, fuzzy inference neural networks (FINNs) working in parallel are employed to achieve a high level of recognition and interpretation. Scenery images are used and it is confirmed that the system has an average of 71.9% accuracy rate in the recognition process and good results in the interpretation process without heuristic knowledge. In addition, it is also confirmed that the proposed system has an ability to extract proper rules for the image recognition and interpretation.

Original languageEnglish
Pages (from-to)1793-1806
Number of pages14
JournalPattern Recognition
Volume35
Issue number8
DOIs
Publication statusPublished - 2002 Aug

Fingerprint

Image recognition
Fuzzy inference
Neural networks
Processing

Keywords

  • Fuzzy inference
  • Image recognition
  • Image understanding
  • Neural network
  • Scenery image

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Scenery image recognition and interpretation using fuzzy inference neural networks. / Iyatomi, Hitoshi; Hagiwara, Masafumi.

In: Pattern Recognition, Vol. 35, No. 8, 08.2002, p. 1793-1806.

Research output: Contribution to journalArticle

@article{d0f9b06a7c7843ba906a6c1b96379d7d,
title = "Scenery image recognition and interpretation using fuzzy inference neural networks",
abstract = "In this paper, we propose a new image recognition and interpretation system. The proposed system is composed of three processes: (1) regional segmentation process; (2) image recognition process; and (3) image interpretation process. As a pre-processing in the regional segmentation process, an input image is divided into some proper regions using techniques based on K-means algorithm. In both the image recognition and the interpretation processes, fuzzy inference neural networks (FINNs) working in parallel are employed to achieve a high level of recognition and interpretation. Scenery images are used and it is confirmed that the system has an average of 71.9{\%} accuracy rate in the recognition process and good results in the interpretation process without heuristic knowledge. In addition, it is also confirmed that the proposed system has an ability to extract proper rules for the image recognition and interpretation.",
keywords = "Fuzzy inference, Image recognition, Image understanding, Neural network, Scenery image",
author = "Hitoshi Iyatomi and Masafumi Hagiwara",
year = "2002",
month = "8",
doi = "10.1016/S0031-3203(01)00171-6",
language = "English",
volume = "35",
pages = "1793--1806",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "8",

}

TY - JOUR

T1 - Scenery image recognition and interpretation using fuzzy inference neural networks

AU - Iyatomi, Hitoshi

AU - Hagiwara, Masafumi

PY - 2002/8

Y1 - 2002/8

N2 - In this paper, we propose a new image recognition and interpretation system. The proposed system is composed of three processes: (1) regional segmentation process; (2) image recognition process; and (3) image interpretation process. As a pre-processing in the regional segmentation process, an input image is divided into some proper regions using techniques based on K-means algorithm. In both the image recognition and the interpretation processes, fuzzy inference neural networks (FINNs) working in parallel are employed to achieve a high level of recognition and interpretation. Scenery images are used and it is confirmed that the system has an average of 71.9% accuracy rate in the recognition process and good results in the interpretation process without heuristic knowledge. In addition, it is also confirmed that the proposed system has an ability to extract proper rules for the image recognition and interpretation.

AB - In this paper, we propose a new image recognition and interpretation system. The proposed system is composed of three processes: (1) regional segmentation process; (2) image recognition process; and (3) image interpretation process. As a pre-processing in the regional segmentation process, an input image is divided into some proper regions using techniques based on K-means algorithm. In both the image recognition and the interpretation processes, fuzzy inference neural networks (FINNs) working in parallel are employed to achieve a high level of recognition and interpretation. Scenery images are used and it is confirmed that the system has an average of 71.9% accuracy rate in the recognition process and good results in the interpretation process without heuristic knowledge. In addition, it is also confirmed that the proposed system has an ability to extract proper rules for the image recognition and interpretation.

KW - Fuzzy inference

KW - Image recognition

KW - Image understanding

KW - Neural network

KW - Scenery image

UR - http://www.scopus.com/inward/record.url?scp=0036681030&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036681030&partnerID=8YFLogxK

U2 - 10.1016/S0031-3203(01)00171-6

DO - 10.1016/S0031-3203(01)00171-6

M3 - Article

AN - SCOPUS:0036681030

VL - 35

SP - 1793

EP - 1806

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 8

ER -