Fusing geometric and appearance-based features for glaucoma diagnosis

Kangrok Oh, Jooyoung Kim, Sangchul Yoon, KyoungYul Seo

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

Abstract

In this paper, we propose to fuse geometric and appearance-based features at the feature-level for automatic glaucoma diagnosis. The cup-to-disc ratio and neuro-retinal rim width variation are extracted as the geometric features based on a coarseto- fine localization method. For the appearancebased feature extraction, the principal components analysis is adopted. Finally, these features are combined at the feature-level based on the random projection and the total error rate minimization classifier. Experimental results on an in-house data set shows that the feature-level fusion can enhance the classification performance comparing with that before fusion.

Original languageEnglish
Title of host publication4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017
PublisherEuropean Association of Geoscientists and Engineers, EAGE
Pages76-85
Number of pages10
ISBN (Electronic)9781941968437
Publication statusPublished - 2017 Jan 1
Event4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017 - Lodz, Poland
Duration: 2017 Sep 182017 Sep 20

Other

Other4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017
CountryPoland
CityLodz
Period17/9/1817/9/20

Fingerprint

Fusion reactions
Electric fuses
Principal component analysis
Feature extraction
Classifiers

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Oh, K., Kim, J., Yoon, S., & Seo, K. (2017). Fusing geometric and appearance-based features for glaucoma diagnosis. In 4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017 (pp. 76-85). European Association of Geoscientists and Engineers, EAGE.
Oh, Kangrok ; Kim, Jooyoung ; Yoon, Sangchul ; Seo, KyoungYul. / Fusing geometric and appearance-based features for glaucoma diagnosis. 4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017. European Association of Geoscientists and Engineers, EAGE, 2017. pp. 76-85
@inproceedings{f6bb6d8340a147e388addbaaf119ba63,
title = "Fusing geometric and appearance-based features for glaucoma diagnosis",
abstract = "In this paper, we propose to fuse geometric and appearance-based features at the feature-level for automatic glaucoma diagnosis. The cup-to-disc ratio and neuro-retinal rim width variation are extracted as the geometric features based on a coarseto- fine localization method. For the appearancebased feature extraction, the principal components analysis is adopted. Finally, these features are combined at the feature-level based on the random projection and the total error rate minimization classifier. Experimental results on an in-house data set shows that the feature-level fusion can enhance the classification performance comparing with that before fusion.",
author = "Kangrok Oh and Jooyoung Kim and Sangchul Yoon and KyoungYul Seo",
year = "2017",
month = "1",
day = "1",
language = "English",
pages = "76--85",
booktitle = "4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017",
publisher = "European Association of Geoscientists and Engineers, EAGE",

}

Oh, K, Kim, J, Yoon, S & Seo, K 2017, Fusing geometric and appearance-based features for glaucoma diagnosis. in 4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017. European Association of Geoscientists and Engineers, EAGE, pp. 76-85, 4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017, Lodz, Poland, 17/9/18.

Fusing geometric and appearance-based features for glaucoma diagnosis. / Oh, Kangrok; Kim, Jooyoung; Yoon, Sangchul; Seo, KyoungYul.

4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017. European Association of Geoscientists and Engineers, EAGE, 2017. p. 76-85.

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

TY - GEN

T1 - Fusing geometric and appearance-based features for glaucoma diagnosis

AU - Oh, Kangrok

AU - Kim, Jooyoung

AU - Yoon, Sangchul

AU - Seo, KyoungYul

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In this paper, we propose to fuse geometric and appearance-based features at the feature-level for automatic glaucoma diagnosis. The cup-to-disc ratio and neuro-retinal rim width variation are extracted as the geometric features based on a coarseto- fine localization method. For the appearancebased feature extraction, the principal components analysis is adopted. Finally, these features are combined at the feature-level based on the random projection and the total error rate minimization classifier. Experimental results on an in-house data set shows that the feature-level fusion can enhance the classification performance comparing with that before fusion.

AB - In this paper, we propose to fuse geometric and appearance-based features at the feature-level for automatic glaucoma diagnosis. The cup-to-disc ratio and neuro-retinal rim width variation are extracted as the geometric features based on a coarseto- fine localization method. For the appearancebased feature extraction, the principal components analysis is adopted. Finally, these features are combined at the feature-level based on the random projection and the total error rate minimization classifier. Experimental results on an in-house data set shows that the feature-level fusion can enhance the classification performance comparing with that before fusion.

UR - http://www.scopus.com/inward/record.url?scp=85060685478&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060685478&partnerID=8YFLogxK

M3 - Conference contribution

SP - 76

EP - 85

BT - 4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017

PB - European Association of Geoscientists and Engineers, EAGE

ER -

Oh K, Kim J, Yoon S, Seo K. Fusing geometric and appearance-based features for glaucoma diagnosis. In 4th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2017. European Association of Geoscientists and Engineers, EAGE. 2017. p. 76-85