Classification of endoscopic images using support vector machines

Decho Surangsrirat, Moiez A. Tapia, Weizhao Zhao

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

2 Citations (Scopus)

Abstract

This paper presents an application of support vector machines (SVMs) to multiclass problem in endoscopic image classification. Many studies have reported that SVMs have met with success in the texture classification problem. As an endoscopic image poses rich information expressed by texture features, we therefore investigate the potential of SVMs in this task. Strategy for multiclass problem based on an ensemble of binary classifiers is also implemented since the traditional SVMs algorithm deals with single label classification problems. The proposed scheme demonstrated an excellent classification result for multiclass problem in endoscopic image classification. We also show how a distortion correction helps further improve the results.

Original languageEnglish
Title of host publicationConference Proceedings - IEEE SOUTHEASTCON
Pages436-439
Number of pages4
DOIs
StatePublished - May 31 2010
EventIEEE SoutheastCon 2010 Conference: Energizing Our Future - Charlotte-Concord, NC, United States
Duration: Mar 18 2010Mar 21 2010

Other

OtherIEEE SoutheastCon 2010 Conference: Energizing Our Future
CountryUnited States
CityCharlotte-Concord, NC
Period3/18/103/21/10

Fingerprint

Support vector machines
Image classification
Textures
Labels
Classifiers

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software
  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Signal Processing

Cite this

Surangsrirat, D., Tapia, M. A., & Zhao, W. (2010). Classification of endoscopic images using support vector machines. In Conference Proceedings - IEEE SOUTHEASTCON (pp. 436-439). [5453834] https://doi.org/10.1109/SECON.2010.5453834

Classification of endoscopic images using support vector machines. / Surangsrirat, Decho; Tapia, Moiez A.; Zhao, Weizhao.

Conference Proceedings - IEEE SOUTHEASTCON. 2010. p. 436-439 5453834.

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

Surangsrirat, D, Tapia, MA & Zhao, W 2010, Classification of endoscopic images using support vector machines. in Conference Proceedings - IEEE SOUTHEASTCON., 5453834, pp. 436-439, IEEE SoutheastCon 2010 Conference: Energizing Our Future, Charlotte-Concord, NC, United States, 3/18/10. https://doi.org/10.1109/SECON.2010.5453834
Surangsrirat D, Tapia MA, Zhao W. Classification of endoscopic images using support vector machines. In Conference Proceedings - IEEE SOUTHEASTCON. 2010. p. 436-439. 5453834 https://doi.org/10.1109/SECON.2010.5453834
Surangsrirat, Decho ; Tapia, Moiez A. ; Zhao, Weizhao. / Classification of endoscopic images using support vector machines. Conference Proceedings - IEEE SOUTHEASTCON. 2010. pp. 436-439
@inproceedings{c421474e016040b8aa25bc6bb8a7d23f,
title = "Classification of endoscopic images using support vector machines",
abstract = "This paper presents an application of support vector machines (SVMs) to multiclass problem in endoscopic image classification. Many studies have reported that SVMs have met with success in the texture classification problem. As an endoscopic image poses rich information expressed by texture features, we therefore investigate the potential of SVMs in this task. Strategy for multiclass problem based on an ensemble of binary classifiers is also implemented since the traditional SVMs algorithm deals with single label classification problems. The proposed scheme demonstrated an excellent classification result for multiclass problem in endoscopic image classification. We also show how a distortion correction helps further improve the results.",
author = "Decho Surangsrirat and Tapia, {Moiez A.} and Weizhao Zhao",
year = "2010",
month = "5",
day = "31",
doi = "10.1109/SECON.2010.5453834",
language = "English",
isbn = "9781424458530",
pages = "436--439",
booktitle = "Conference Proceedings - IEEE SOUTHEASTCON",

}

TY - GEN

T1 - Classification of endoscopic images using support vector machines

AU - Surangsrirat, Decho

AU - Tapia, Moiez A.

AU - Zhao, Weizhao

PY - 2010/5/31

Y1 - 2010/5/31

N2 - This paper presents an application of support vector machines (SVMs) to multiclass problem in endoscopic image classification. Many studies have reported that SVMs have met with success in the texture classification problem. As an endoscopic image poses rich information expressed by texture features, we therefore investigate the potential of SVMs in this task. Strategy for multiclass problem based on an ensemble of binary classifiers is also implemented since the traditional SVMs algorithm deals with single label classification problems. The proposed scheme demonstrated an excellent classification result for multiclass problem in endoscopic image classification. We also show how a distortion correction helps further improve the results.

AB - This paper presents an application of support vector machines (SVMs) to multiclass problem in endoscopic image classification. Many studies have reported that SVMs have met with success in the texture classification problem. As an endoscopic image poses rich information expressed by texture features, we therefore investigate the potential of SVMs in this task. Strategy for multiclass problem based on an ensemble of binary classifiers is also implemented since the traditional SVMs algorithm deals with single label classification problems. The proposed scheme demonstrated an excellent classification result for multiclass problem in endoscopic image classification. We also show how a distortion correction helps further improve the results.

UR - http://www.scopus.com/inward/record.url?scp=77952697553&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952697553&partnerID=8YFLogxK

U2 - 10.1109/SECON.2010.5453834

DO - 10.1109/SECON.2010.5453834

M3 - Conference contribution

SN - 9781424458530

SP - 436

EP - 439

BT - Conference Proceedings - IEEE SOUTHEASTCON

ER -