A new system for segmentation and recognition of scenery images

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a new system for segmentation and recognition of scenery images. Most of the conventional methods for image recognition are based on rules or pattern matching. It is true that they have high accuracy. However, the generalization ability is not sufficient and they require heuristic knowledge. In addition, these methods are used on the assumption that images are segmented appropriately. The proposed system alleviates these shortcomings by effective combination of K-mean-type algorithm [4], Back Propagation algorithm (BP) and Fuzzy Inference Neural Network (FINN) [8].

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages2548-2553
Number of pages6
Volume4
Publication statusPublished - 2001
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States
Duration: 2001 Jul 152001 Jul 19

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'01)
CountryUnited States
CityWashington, DC
Period01/7/1501/7/19

Fingerprint

Image recognition
Backpropagation algorithms
Pattern matching
Fuzzy inference
Neural networks

ASJC Scopus subject areas

  • Software

Cite this

Kudo, S., & Hagiwara, M. (2001). A new system for segmentation and recognition of scenery images. In Proceedings of the International Joint Conference on Neural Networks (Vol. 4, pp. 2548-2553)

A new system for segmentation and recognition of scenery images. / Kudo, S.; Hagiwara, Masafumi.

Proceedings of the International Joint Conference on Neural Networks. Vol. 4 2001. p. 2548-2553.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kudo, S & Hagiwara, M 2001, A new system for segmentation and recognition of scenery images. in Proceedings of the International Joint Conference on Neural Networks. vol. 4, pp. 2548-2553, International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States, 01/7/15.
Kudo S, Hagiwara M. A new system for segmentation and recognition of scenery images. In Proceedings of the International Joint Conference on Neural Networks. Vol. 4. 2001. p. 2548-2553
Kudo, S. ; Hagiwara, Masafumi. / A new system for segmentation and recognition of scenery images. Proceedings of the International Joint Conference on Neural Networks. Vol. 4 2001. pp. 2548-2553
@inproceedings{56d7a4cb8c6f4167a260603e78989146,
title = "A new system for segmentation and recognition of scenery images",
abstract = "This paper proposes a new system for segmentation and recognition of scenery images. Most of the conventional methods for image recognition are based on rules or pattern matching. It is true that they have high accuracy. However, the generalization ability is not sufficient and they require heuristic knowledge. In addition, these methods are used on the assumption that images are segmented appropriately. The proposed system alleviates these shortcomings by effective combination of K-mean-type algorithm [4], Back Propagation algorithm (BP) and Fuzzy Inference Neural Network (FINN) [8].",
author = "S. Kudo and Masafumi Hagiwara",
year = "2001",
language = "English",
volume = "4",
pages = "2548--2553",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - A new system for segmentation and recognition of scenery images

AU - Kudo, S.

AU - Hagiwara, Masafumi

PY - 2001

Y1 - 2001

N2 - This paper proposes a new system for segmentation and recognition of scenery images. Most of the conventional methods for image recognition are based on rules or pattern matching. It is true that they have high accuracy. However, the generalization ability is not sufficient and they require heuristic knowledge. In addition, these methods are used on the assumption that images are segmented appropriately. The proposed system alleviates these shortcomings by effective combination of K-mean-type algorithm [4], Back Propagation algorithm (BP) and Fuzzy Inference Neural Network (FINN) [8].

AB - This paper proposes a new system for segmentation and recognition of scenery images. Most of the conventional methods for image recognition are based on rules or pattern matching. It is true that they have high accuracy. However, the generalization ability is not sufficient and they require heuristic knowledge. In addition, these methods are used on the assumption that images are segmented appropriately. The proposed system alleviates these shortcomings by effective combination of K-mean-type algorithm [4], Back Propagation algorithm (BP) and Fuzzy Inference Neural Network (FINN) [8].

UR - http://www.scopus.com/inward/record.url?scp=0034861339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034861339&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034861339

VL - 4

SP - 2548

EP - 2553

BT - Proceedings of the International Joint Conference on Neural Networks

ER -