Region-based binary tree representation for image classification

Zhiyong Wang; Dagan Feng; Zheru Chi

doi:10.1109/ICNNSP.2003.1279254

Region-based binary tree representation for image classification

Zhiyong Wang, Dagan Feng, 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

5 Citations (Scopus)

Abstract

Image classification is a very challenging problem due to lack of effective representations. In this paper, a region-based binary tree representation incorporating with adaptive processing of data structures is proposed to address this problem. After an image is segmented, a binary tree is established to characterize its contents by using region merging method. Finally, an adaptive processing of data structure algorithm is employed to perform the classification task with binary tree representation. Experimental results on seven categories of scenery images show this region-based structural representation is superior to our previous work based on quadtree representation.

Original language	English
Title of host publication	Proceedings of 2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03
Pages	232-235
Number of pages	4
Volume	1
DOIs	https://doi.org/10.1109/ICNNSP.2003.1279254
Publication status	Published - 1 Dec 2003
Event	2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03 - Nanjing, China Duration: 14 Dec 2003 → 17 Dec 2003

Conference

Conference	2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03
Country/Territory	China
City	Nanjing
Period	14/12/03 → 17/12/03

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

More information

10.1109/ICNNSP.2003.1279254

Cite this

@inproceedings{c98aa9c553b2487a91b65b9e74fa957a,

title = "Region-based binary tree representation for image classification",

abstract = "Image classification is a very challenging problem due to lack of effective representations. In this paper, a region-based binary tree representation incorporating with adaptive processing of data structures is proposed to address this problem. After an image is segmented, a binary tree is established to characterize its contents by using region merging method. Finally, an adaptive processing of data structure algorithm is employed to perform the classification task with binary tree representation. Experimental results on seven categories of scenery images show this region-based structural representation is superior to our previous work based on quadtree representation.",

author = "Zhiyong Wang and Dagan Feng and Zheru Chi",

year = "2003",

month = dec,

day = "1",

doi = "10.1109/ICNNSP.2003.1279254",

language = "English",

isbn = "0780377028",

volume = "1",

pages = "232--235",

booktitle = "Proceedings of 2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03",

note = "2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03 ; Conference date: 14-12-2003 Through 17-12-2003",

}

Wang, Z, Feng, D & Chi, Z 2003, Region-based binary tree representation for image classification. in Proceedings of 2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03. vol. 1, 1279254, pp. 232-235, 2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03, Nanjing, China, 14/12/03. https://doi.org/10.1109/ICNNSP.2003.1279254

Region-based binary tree representation for image classification. / Wang, Zhiyong; Feng, Dagan; Chi, Zheru.
Proceedings of 2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03. Vol. 1 2003. p. 232-235 1279254.

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

TY - GEN

T1 - Region-based binary tree representation for image classification

AU - Wang, Zhiyong

AU - Feng, Dagan

AU - Chi, Zheru

PY - 2003/12/1

Y1 - 2003/12/1

N2 - Image classification is a very challenging problem due to lack of effective representations. In this paper, a region-based binary tree representation incorporating with adaptive processing of data structures is proposed to address this problem. After an image is segmented, a binary tree is established to characterize its contents by using region merging method. Finally, an adaptive processing of data structure algorithm is employed to perform the classification task with binary tree representation. Experimental results on seven categories of scenery images show this region-based structural representation is superior to our previous work based on quadtree representation.

AB - Image classification is a very challenging problem due to lack of effective representations. In this paper, a region-based binary tree representation incorporating with adaptive processing of data structures is proposed to address this problem. After an image is segmented, a binary tree is established to characterize its contents by using region merging method. Finally, an adaptive processing of data structure algorithm is employed to perform the classification task with binary tree representation. Experimental results on seven categories of scenery images show this region-based structural representation is superior to our previous work based on quadtree representation.

UR - http://www.scopus.com/inward/record.url?scp=15944386617&partnerID=8YFLogxK

U2 - 10.1109/ICNNSP.2003.1279254

DO - 10.1109/ICNNSP.2003.1279254

M3 - Conference article published in proceeding or book

SN - 0780377028

SN - 9780780377028

VL - 1

SP - 232

EP - 235

BT - Proceedings of 2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03

T2 - 2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03

Y2 - 14 December 2003 through 17 December 2003

ER -

Region-based binary tree representation for image classification

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this