Image classification with structured self-organization map

Z. Wang; M. Hagenbuchner; A. C. Tsoi; S. Y. Cho; Zheru Chi

Image classification with structured self-organization map

Z. Wang, M. Hagenbuchner, A. C. Tsoi, S. Y. Cho, Zheru Chi

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

14 Citations (Scopus)

Abstract

Adaptive processing of structured data using supervised learning scheme has been successfully applied to many domains, e.g., molecular biology, image classification and retrieval. A self organizing map (SOM) type algorithm for processing of structured data using an unsupervised learning approach has recently been proposed. In this paper, we present an approach using quadtree representation to extract an image structure, and the application of such structured SOM to image classification problems. Encouraging results achieved by using only six simple visual features show that the structured SOM works well for structural information.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Pages	1918-1923
Number of pages	6
Publication status	Published - 1 Jan 2002
Event	2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States Duration: 12 May 2002 → 17 May 2002

Conference

Conference	2002 International Joint Conference on Neural Networks (IJCNN '02)
Country/Territory	United States
City	Honolulu, HI
Period	12/05/02 → 17/05/02

ASJC Scopus subject areas

Software
Artificial Intelligence

Cite this

@inproceedings{4d439b85e1714dcba294705099583212,

title = "Image classification with structured self-organization map",

abstract = "Adaptive processing of structured data using supervised learning scheme has been successfully applied to many domains, e.g., molecular biology, image classification and retrieval. A self organizing map (SOM) type algorithm for processing of structured data using an unsupervised learning approach has recently been proposed. In this paper, we present an approach using quadtree representation to extract an image structure, and the application of such structured SOM to image classification problems. Encouraging results achieved by using only six simple visual features show that the structured SOM works well for structural information.",

author = "Z. Wang and M. Hagenbuchner and Tsoi, {A. C.} and Cho, {S. Y.} and Zheru Chi",

year = "2002",

month = jan,

day = "1",

language = "English",

pages = "1918--1923",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

note = "2002 International Joint Conference on Neural Networks (IJCNN '02) ; Conference date: 12-05-2002 Through 17-05-2002",

}

TY - GEN

T1 - Image classification with structured self-organization map

AU - Wang, Z.

AU - Hagenbuchner, M.

AU - Tsoi, A. C.

AU - Cho, S. Y.

AU - Chi, Zheru

PY - 2002/1/1

Y1 - 2002/1/1

N2 - Adaptive processing of structured data using supervised learning scheme has been successfully applied to many domains, e.g., molecular biology, image classification and retrieval. A self organizing map (SOM) type algorithm for processing of structured data using an unsupervised learning approach has recently been proposed. In this paper, we present an approach using quadtree representation to extract an image structure, and the application of such structured SOM to image classification problems. Encouraging results achieved by using only six simple visual features show that the structured SOM works well for structural information.

AB - Adaptive processing of structured data using supervised learning scheme has been successfully applied to many domains, e.g., molecular biology, image classification and retrieval. A self organizing map (SOM) type algorithm for processing of structured data using an unsupervised learning approach has recently been proposed. In this paper, we present an approach using quadtree representation to extract an image structure, and the application of such structured SOM to image classification problems. Encouraging results achieved by using only six simple visual features show that the structured SOM works well for structural information.

UR - http://www.scopus.com/inward/record.url?scp=0036085394&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SP - 1918

EP - 1923

BT - Proceedings of the International Joint Conference on Neural Networks

T2 - 2002 International Joint Conference on Neural Networks (IJCNN '02)

Y2 - 12 May 2002 through 17 May 2002

ER -

Image classification with structured self-organization map

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this