Automatic Segmentation of Blood Vessels in Colour Retinal Images using Spatial Gabor Filter and Multiscale Analysis

P. C. Siddalingaswamy, K. Gopalakrishna Prabhu

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

1 Citation (Scopus)

Abstract

Retinal blood vessels are significant anatomical structures in ophthalmic images. Automatic segmentation of blood vessels is one of the important steps in computer aided diagnosis system for the detection of diseases such as Diabetic Retinopathy that affect human retina. We propose a method for the segmentation of retinal blood vessels using Spatial Gabor filters as they can be tuned to the specific frequency and orientation. A new parameter is defined to facilitate filtering at different scales to detect the vessels of varying thicknesses. The method is tested on forty colour retinal images of DRIVE (Digital Retinal Images for Vessel Extraction) database with manual segmentations as ground truth. An overall accuracy of 84.22% is achieved for segmentation of retinal blood vessels.

Original languageEnglish
Title of host publication13th International Conference on Biomedical Engineering - ICBME 2008
Pages274-276
Number of pages3
Volume23
DOIs
Publication statusPublished - 2009
Event13th International Conference on Biomedical Engineering, ICBME 2008 - , Singapore
Duration: 03-12-200806-12-2008

Conference

Conference13th International Conference on Biomedical Engineering, ICBME 2008
CountrySingapore
Period03-12-0806-12-08

Fingerprint

Gabor filters
Blood vessels
Color
Computer aided diagnosis

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Bioengineering

Cite this

Siddalingaswamy, P. C., & Prabhu, K. G. (2009). Automatic Segmentation of Blood Vessels in Colour Retinal Images using Spatial Gabor Filter and Multiscale Analysis. In 13th International Conference on Biomedical Engineering - ICBME 2008 (Vol. 23, pp. 274-276) https://doi.org/10.1007/978-3-540-92841-6_66
Siddalingaswamy, P. C. ; Prabhu, K. Gopalakrishna. / Automatic Segmentation of Blood Vessels in Colour Retinal Images using Spatial Gabor Filter and Multiscale Analysis. 13th International Conference on Biomedical Engineering - ICBME 2008. Vol. 23 2009. pp. 274-276
@inproceedings{7cdc8cb016014af984e4322ef1753166,
title = "Automatic Segmentation of Blood Vessels in Colour Retinal Images using Spatial Gabor Filter and Multiscale Analysis",
abstract = "Retinal blood vessels are significant anatomical structures in ophthalmic images. Automatic segmentation of blood vessels is one of the important steps in computer aided diagnosis system for the detection of diseases such as Diabetic Retinopathy that affect human retina. We propose a method for the segmentation of retinal blood vessels using Spatial Gabor filters as they can be tuned to the specific frequency and orientation. A new parameter is defined to facilitate filtering at different scales to detect the vessels of varying thicknesses. The method is tested on forty colour retinal images of DRIVE (Digital Retinal Images for Vessel Extraction) database with manual segmentations as ground truth. An overall accuracy of 84.22{\%} is achieved for segmentation of retinal blood vessels.",
author = "Siddalingaswamy, {P. C.} and Prabhu, {K. Gopalakrishna}",
year = "2009",
doi = "10.1007/978-3-540-92841-6_66",
language = "English",
isbn = "9783540928409",
volume = "23",
pages = "274--276",
booktitle = "13th International Conference on Biomedical Engineering - ICBME 2008",

}

Siddalingaswamy, PC & Prabhu, KG 2009, Automatic Segmentation of Blood Vessels in Colour Retinal Images using Spatial Gabor Filter and Multiscale Analysis. in 13th International Conference on Biomedical Engineering - ICBME 2008. vol. 23, pp. 274-276, 13th International Conference on Biomedical Engineering, ICBME 2008, Singapore, 03-12-08. https://doi.org/10.1007/978-3-540-92841-6_66

Automatic Segmentation of Blood Vessels in Colour Retinal Images using Spatial Gabor Filter and Multiscale Analysis. / Siddalingaswamy, P. C.; Prabhu, K. Gopalakrishna.

13th International Conference on Biomedical Engineering - ICBME 2008. Vol. 23 2009. p. 274-276.

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

TY - GEN

T1 - Automatic Segmentation of Blood Vessels in Colour Retinal Images using Spatial Gabor Filter and Multiscale Analysis

AU - Siddalingaswamy, P. C.

AU - Prabhu, K. Gopalakrishna

PY - 2009

Y1 - 2009

N2 - Retinal blood vessels are significant anatomical structures in ophthalmic images. Automatic segmentation of blood vessels is one of the important steps in computer aided diagnosis system for the detection of diseases such as Diabetic Retinopathy that affect human retina. We propose a method for the segmentation of retinal blood vessels using Spatial Gabor filters as they can be tuned to the specific frequency and orientation. A new parameter is defined to facilitate filtering at different scales to detect the vessels of varying thicknesses. The method is tested on forty colour retinal images of DRIVE (Digital Retinal Images for Vessel Extraction) database with manual segmentations as ground truth. An overall accuracy of 84.22% is achieved for segmentation of retinal blood vessels.

AB - Retinal blood vessels are significant anatomical structures in ophthalmic images. Automatic segmentation of blood vessels is one of the important steps in computer aided diagnosis system for the detection of diseases such as Diabetic Retinopathy that affect human retina. We propose a method for the segmentation of retinal blood vessels using Spatial Gabor filters as they can be tuned to the specific frequency and orientation. A new parameter is defined to facilitate filtering at different scales to detect the vessels of varying thicknesses. The method is tested on forty colour retinal images of DRIVE (Digital Retinal Images for Vessel Extraction) database with manual segmentations as ground truth. An overall accuracy of 84.22% is achieved for segmentation of retinal blood vessels.

UR - http://www.scopus.com/inward/record.url?scp=84891954339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891954339&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-92841-6_66

DO - 10.1007/978-3-540-92841-6_66

M3 - Conference contribution

SN - 9783540928409

VL - 23

SP - 274

EP - 276

BT - 13th International Conference on Biomedical Engineering - ICBME 2008

ER -