The Role of Color and Texture Features in Glaucoma Detection

Sumaiya Pathan, Preetham Kumar, Radhika M. Pai

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

Abstract

Glaucoma is considered as a neurodegenerative disease and one of the leading cause for vision loss. A computer aided diagnostic tool for glaucoma detection is of primary importance in early detection. This paper presents a novel computer based automated glaucoma detection method. Unlike the present state-of-art approaches, the proposed method eliminates the segmentation of retinal structures and extracts color and texture features from the blood vessel in-painted fundus images. Blood vessels are considered as noisy pixels and are eliminated prior to feature extraction. The color and texture features provide information which is clinically significant for characterization of retinal fundus images as glaucoma and healthy. The proposed approach achieved an accuracy of 94.7% with Artificial Neural Network (ANN) classifier and 92% with Support Vector Machine (SVM) classifier.

Original languageEnglish
Title of host publication2018 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages526-530
Number of pages5
ISBN (Electronic)9781538653142
DOIs
Publication statusPublished - 30-11-2018
Event7th International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018 - Bangalore, India
Duration: 19-09-201822-09-2018

Conference

Conference7th International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018
CountryIndia
CityBangalore
Period19-09-1822-09-18

Fingerprint

Blood vessels
Classifiers
Textures
Neurodegenerative diseases
Color
Support vector machines
Feature extraction
Pixels
Neural networks

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems

Cite this

Pathan, S., Kumar, P., & Pai, R. M. (2018). The Role of Color and Texture Features in Glaucoma Detection. In 2018 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018 (pp. 526-530). [8554854] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICACCI.2018.8554854
Pathan, Sumaiya ; Kumar, Preetham ; Pai, Radhika M. / The Role of Color and Texture Features in Glaucoma Detection. 2018 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 526-530
@inproceedings{a29eb03e6f8246398f211630d09dfc9f,
title = "The Role of Color and Texture Features in Glaucoma Detection",
abstract = "Glaucoma is considered as a neurodegenerative disease and one of the leading cause for vision loss. A computer aided diagnostic tool for glaucoma detection is of primary importance in early detection. This paper presents a novel computer based automated glaucoma detection method. Unlike the present state-of-art approaches, the proposed method eliminates the segmentation of retinal structures and extracts color and texture features from the blood vessel in-painted fundus images. Blood vessels are considered as noisy pixels and are eliminated prior to feature extraction. The color and texture features provide information which is clinically significant for characterization of retinal fundus images as glaucoma and healthy. The proposed approach achieved an accuracy of 94.7{\%} with Artificial Neural Network (ANN) classifier and 92{\%} with Support Vector Machine (SVM) classifier.",
author = "Sumaiya Pathan and Preetham Kumar and Pai, {Radhika M.}",
year = "2018",
month = "11",
day = "30",
doi = "10.1109/ICACCI.2018.8554854",
language = "English",
pages = "526--530",
booktitle = "2018 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Pathan, S, Kumar, P & Pai, RM 2018, The Role of Color and Texture Features in Glaucoma Detection. in 2018 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018., 8554854, Institute of Electrical and Electronics Engineers Inc., pp. 526-530, 7th International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018, Bangalore, India, 19-09-18. https://doi.org/10.1109/ICACCI.2018.8554854

The Role of Color and Texture Features in Glaucoma Detection. / Pathan, Sumaiya; Kumar, Preetham; Pai, Radhika M.

2018 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 526-530 8554854.

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

TY - GEN

T1 - The Role of Color and Texture Features in Glaucoma Detection

AU - Pathan, Sumaiya

AU - Kumar, Preetham

AU - Pai, Radhika M.

PY - 2018/11/30

Y1 - 2018/11/30

N2 - Glaucoma is considered as a neurodegenerative disease and one of the leading cause for vision loss. A computer aided diagnostic tool for glaucoma detection is of primary importance in early detection. This paper presents a novel computer based automated glaucoma detection method. Unlike the present state-of-art approaches, the proposed method eliminates the segmentation of retinal structures and extracts color and texture features from the blood vessel in-painted fundus images. Blood vessels are considered as noisy pixels and are eliminated prior to feature extraction. The color and texture features provide information which is clinically significant for characterization of retinal fundus images as glaucoma and healthy. The proposed approach achieved an accuracy of 94.7% with Artificial Neural Network (ANN) classifier and 92% with Support Vector Machine (SVM) classifier.

AB - Glaucoma is considered as a neurodegenerative disease and one of the leading cause for vision loss. A computer aided diagnostic tool for glaucoma detection is of primary importance in early detection. This paper presents a novel computer based automated glaucoma detection method. Unlike the present state-of-art approaches, the proposed method eliminates the segmentation of retinal structures and extracts color and texture features from the blood vessel in-painted fundus images. Blood vessels are considered as noisy pixels and are eliminated prior to feature extraction. The color and texture features provide information which is clinically significant for characterization of retinal fundus images as glaucoma and healthy. The proposed approach achieved an accuracy of 94.7% with Artificial Neural Network (ANN) classifier and 92% with Support Vector Machine (SVM) classifier.

UR - http://www.scopus.com/inward/record.url?scp=85060035645&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060035645&partnerID=8YFLogxK

U2 - 10.1109/ICACCI.2018.8554854

DO - 10.1109/ICACCI.2018.8554854

M3 - Conference contribution

SP - 526

EP - 530

BT - 2018 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Pathan S, Kumar P, Pai RM. The Role of Color and Texture Features in Glaucoma Detection. In 2018 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 526-530. 8554854 https://doi.org/10.1109/ICACCI.2018.8554854