Methods to enhance digital fundus image for diabetic retinopathy detection

Husna Ab Rahim, Ahmad Syahir Ibrahim, Wan Mimi Diyana Wan Zaki, Aini Hussain

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

10 Citations (Scopus)

Abstract

Digital fundus images (DFIs) are crucial in detecting pathological phenomenon that would lead to various diseases. However, DFI has multiple contrast and illumination problems which makes enhancement a necessity. Consequently, DFI must be enhanced to allow for better visualization in order to facilitate ophthalmologists to carry out their diagnosis. In this work, an investigation of three enhancement methods namely, Histogram Equalization(HE), Contrast Limited Adaptive Histogram Equalization(CLAHE) and Mahalanobis Distance (MD), were conducted on the digital fundus images and the results are qualitatively presented using histogram representation and image product quality. The result shows that the MD is the best algorithm for the application of blood vessels image enhancement.

Original languageEnglish
Title of host publicationProceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014
PublisherIEEE Computer Society
Pages221-224
Number of pages4
ISBN (Print)9781479915323
DOIs
Publication statusPublished - 2014
Event2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014 - Kuala Lumpur
Duration: 7 Mar 20149 Mar 2014

Other

Other2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014
CityKuala Lumpur
Period7/3/149/3/14

Fingerprint

Image enhancement
Blood vessels
Visualization
Lighting

Keywords

  • blood vessel detection
  • Diabetic Retinopathy detection
  • Fundus Image enhancement

ASJC Scopus subject areas

  • Signal Processing

Cite this

Rahim, H. A., Ibrahim, A. S., Wan Zaki, W. M. D., & Hussain, A. (2014). Methods to enhance digital fundus image for diabetic retinopathy detection. In Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014 (pp. 221-224). [6805752] IEEE Computer Society. https://doi.org/10.1109/CSPA.2014.6805752

Methods to enhance digital fundus image for diabetic retinopathy detection. / Rahim, Husna Ab; Ibrahim, Ahmad Syahir; Wan Zaki, Wan Mimi Diyana; Hussain, Aini.

Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014. IEEE Computer Society, 2014. p. 221-224 6805752.

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

Rahim, HA, Ibrahim, AS, Wan Zaki, WMD & Hussain, A 2014, Methods to enhance digital fundus image for diabetic retinopathy detection. in Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014., 6805752, IEEE Computer Society, pp. 221-224, 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014, Kuala Lumpur, 7/3/14. https://doi.org/10.1109/CSPA.2014.6805752
Rahim HA, Ibrahim AS, Wan Zaki WMD, Hussain A. Methods to enhance digital fundus image for diabetic retinopathy detection. In Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014. IEEE Computer Society. 2014. p. 221-224. 6805752 https://doi.org/10.1109/CSPA.2014.6805752
Rahim, Husna Ab ; Ibrahim, Ahmad Syahir ; Wan Zaki, Wan Mimi Diyana ; Hussain, Aini. / Methods to enhance digital fundus image for diabetic retinopathy detection. Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014. IEEE Computer Society, 2014. pp. 221-224
@inproceedings{e787e217fa8849eb9fa05c4367d08945,
title = "Methods to enhance digital fundus image for diabetic retinopathy detection",
abstract = "Digital fundus images (DFIs) are crucial in detecting pathological phenomenon that would lead to various diseases. However, DFI has multiple contrast and illumination problems which makes enhancement a necessity. Consequently, DFI must be enhanced to allow for better visualization in order to facilitate ophthalmologists to carry out their diagnosis. In this work, an investigation of three enhancement methods namely, Histogram Equalization(HE), Contrast Limited Adaptive Histogram Equalization(CLAHE) and Mahalanobis Distance (MD), were conducted on the digital fundus images and the results are qualitatively presented using histogram representation and image product quality. The result shows that the MD is the best algorithm for the application of blood vessels image enhancement.",
keywords = "blood vessel detection, Diabetic Retinopathy detection, Fundus Image enhancement",
author = "Rahim, {Husna Ab} and Ibrahim, {Ahmad Syahir} and {Wan Zaki}, {Wan Mimi Diyana} and Aini Hussain",
year = "2014",
doi = "10.1109/CSPA.2014.6805752",
language = "English",
isbn = "9781479915323",
pages = "221--224",
booktitle = "Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Methods to enhance digital fundus image for diabetic retinopathy detection

AU - Rahim, Husna Ab

AU - Ibrahim, Ahmad Syahir

AU - Wan Zaki, Wan Mimi Diyana

AU - Hussain, Aini

PY - 2014

Y1 - 2014

N2 - Digital fundus images (DFIs) are crucial in detecting pathological phenomenon that would lead to various diseases. However, DFI has multiple contrast and illumination problems which makes enhancement a necessity. Consequently, DFI must be enhanced to allow for better visualization in order to facilitate ophthalmologists to carry out their diagnosis. In this work, an investigation of three enhancement methods namely, Histogram Equalization(HE), Contrast Limited Adaptive Histogram Equalization(CLAHE) and Mahalanobis Distance (MD), were conducted on the digital fundus images and the results are qualitatively presented using histogram representation and image product quality. The result shows that the MD is the best algorithm for the application of blood vessels image enhancement.

AB - Digital fundus images (DFIs) are crucial in detecting pathological phenomenon that would lead to various diseases. However, DFI has multiple contrast and illumination problems which makes enhancement a necessity. Consequently, DFI must be enhanced to allow for better visualization in order to facilitate ophthalmologists to carry out their diagnosis. In this work, an investigation of three enhancement methods namely, Histogram Equalization(HE), Contrast Limited Adaptive Histogram Equalization(CLAHE) and Mahalanobis Distance (MD), were conducted on the digital fundus images and the results are qualitatively presented using histogram representation and image product quality. The result shows that the MD is the best algorithm for the application of blood vessels image enhancement.

KW - blood vessel detection

KW - Diabetic Retinopathy detection

KW - Fundus Image enhancement

UR - http://www.scopus.com/inward/record.url?scp=84901660722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901660722&partnerID=8YFLogxK

U2 - 10.1109/CSPA.2014.6805752

DO - 10.1109/CSPA.2014.6805752

M3 - Conference contribution

AN - SCOPUS:84901660722

SN - 9781479915323

SP - 221

EP - 224

BT - Proceedings - 2014 IEEE 10th International Colloquium on Signal Processing and Its Applications, CSPA 2014

PB - IEEE Computer Society

ER -