A new system for segmentation and recognition of scenery images

S. Kudo; M. Hagiwara

A new system for segmentation and recognition of scenery images

Department of Information and Computer Science

Research output: Contribution to conference › Paper › peer-review

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 language	English
Pages	2548-2553
Number of pages	6
Publication status	Published - 2001 Jan 1
Event	International Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States Duration: 2001 Jul 15 → 2001 Jul 19

Other

Other	International Joint Conference on Neural Networks (IJCNN'01)
Country/Territory	United States
City	Washington, DC
Period	01/7/15 → 01/7/19

ASJC Scopus subject areas

Software
Artificial Intelligence

Cite this

@conference{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 M. Hagiwara",

year = "2001",

month = jan,

day = "1",

language = "English",

pages = "2548--2553",

note = "International Joint Conference on Neural Networks (IJCNN'01) ; Conference date: 15-07-2001 Through 19-07-2001",

}

TY - CONF

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

AU - Kudo, S.

AU - Hagiwara, M.

PY - 2001/1/1

Y1 - 2001/1/1

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 - Paper

AN - SCOPUS:0034861339

SP - 2548

EP - 2553

T2 - International Joint Conference on Neural Networks (IJCNN'01)

Y2 - 15 July 2001 through 19 July 2001

ER -

A new system for segmentation and recognition of scenery images

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this