Segmentation of blood vessels in fundus color images by radon transform and morphological reconstruction

Reza Pourreza; Hamidreza Pourreza; Touka Banaee

doi:10.1109/IWACI.2010.5585121

Segmentation of blood vessels in fundus color images by radon transform and morphological reconstruction

Reza Pourreza, Hamidreza Pourreza, Touka Banaee

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

12 Scopus citations

Abstract

In this paper we have presented an algorithm for vessel detection in retinal color images which works based on local Radon transform and morphological reconstruction. In our previous work, the algorithm was applied to conjunctival images and the performance was evaluated subjectively. In this work an extended version of the algorithm is applied to retinal images and our aim is to detect vessels in retinal images of patient people and make a good discrimination between blood vessels and other pathological elements like microaneurysms and hemorrhages which have the same color as vessels. The algorithm performance was evaluated numerically by applying it to DRIVE image database and the achieved ROC curve demonstrates its high accuracy.

Original language	English (US)
Title of host publication	3rd International Workshop on Advanced Computational Intelligence, IWACI 2010
Pages	522-526
Number of pages	5
DOIs	https://doi.org/10.1109/IWACI.2010.5585121
State	Published - 2010
Externally published	Yes
Event	3rd International Workshop on Advanced Computational Intelligence, IWACI 2010 - Suzhou, China Duration: Aug 25 2010 → Aug 27 2010

Publication series

Name	3rd International Workshop on Advanced Computational Intelligence, IWACI 2010

Conference

Conference	3rd International Workshop on Advanced Computational Intelligence, IWACI 2010
Country/Territory	China
City	Suzhou
Period	8/25/10 → 8/27/10

ASJC Scopus subject areas

Artificial Intelligence
Computational Theory and Mathematics

Access to Document

10.1109/IWACI.2010.5585121

Cite this

Pourreza, R., Pourreza, H., & Banaee, T. (2010). Segmentation of blood vessels in fundus color images by radon transform and morphological reconstruction. In 3rd International Workshop on Advanced Computational Intelligence, IWACI 2010 (pp. 522-526). Article 5585121 (3rd International Workshop on Advanced Computational Intelligence, IWACI 2010). https://doi.org/10.1109/IWACI.2010.5585121

Segmentation of blood vessels in fundus color images by radon transform and morphological reconstruction. / Pourreza, Reza; Pourreza, Hamidreza; Banaee, Touka.
3rd International Workshop on Advanced Computational Intelligence, IWACI 2010. 2010. p. 522-526 5585121 (3rd International Workshop on Advanced Computational Intelligence, IWACI 2010).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Pourreza, R, Pourreza, H & Banaee, T 2010, Segmentation of blood vessels in fundus color images by radon transform and morphological reconstruction. in 3rd International Workshop on Advanced Computational Intelligence, IWACI 2010., 5585121, 3rd International Workshop on Advanced Computational Intelligence, IWACI 2010, pp. 522-526, 3rd International Workshop on Advanced Computational Intelligence, IWACI 2010, Suzhou, China, 8/25/10. https://doi.org/10.1109/IWACI.2010.5585121

@inproceedings{f0161ccae25c404a898e632f5354e896,

title = "Segmentation of blood vessels in fundus color images by radon transform and morphological reconstruction",

abstract = "In this paper we have presented an algorithm for vessel detection in retinal color images which works based on local Radon transform and morphological reconstruction. In our previous work, the algorithm was applied to conjunctival images and the performance was evaluated subjectively. In this work an extended version of the algorithm is applied to retinal images and our aim is to detect vessels in retinal images of patient people and make a good discrimination between blood vessels and other pathological elements like microaneurysms and hemorrhages which have the same color as vessels. The algorithm performance was evaluated numerically by applying it to DRIVE image database and the achieved ROC curve demonstrates its high accuracy.",

author = "Reza Pourreza and Hamidreza Pourreza and Touka Banaee",

year = "2010",

doi = "10.1109/IWACI.2010.5585121",

language = "English (US)",

isbn = "9781424463343",

series = "3rd International Workshop on Advanced Computational Intelligence, IWACI 2010",

pages = "522--526",

booktitle = "3rd International Workshop on Advanced Computational Intelligence, IWACI 2010",

}

TY - GEN

T1 - Segmentation of blood vessels in fundus color images by radon transform and morphological reconstruction

AU - Pourreza, Reza

AU - Pourreza, Hamidreza

AU - Banaee, Touka

PY - 2010

Y1 - 2010

N2 - In this paper we have presented an algorithm for vessel detection in retinal color images which works based on local Radon transform and morphological reconstruction. In our previous work, the algorithm was applied to conjunctival images and the performance was evaluated subjectively. In this work an extended version of the algorithm is applied to retinal images and our aim is to detect vessels in retinal images of patient people and make a good discrimination between blood vessels and other pathological elements like microaneurysms and hemorrhages which have the same color as vessels. The algorithm performance was evaluated numerically by applying it to DRIVE image database and the achieved ROC curve demonstrates its high accuracy.

AB - In this paper we have presented an algorithm for vessel detection in retinal color images which works based on local Radon transform and morphological reconstruction. In our previous work, the algorithm was applied to conjunctival images and the performance was evaluated subjectively. In this work an extended version of the algorithm is applied to retinal images and our aim is to detect vessels in retinal images of patient people and make a good discrimination between blood vessels and other pathological elements like microaneurysms and hemorrhages which have the same color as vessels. The algorithm performance was evaluated numerically by applying it to DRIVE image database and the achieved ROC curve demonstrates its high accuracy.

UR - http://www.scopus.com/inward/record.url?scp=78149451854&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149451854&partnerID=8YFLogxK

U2 - 10.1109/IWACI.2010.5585121

DO - 10.1109/IWACI.2010.5585121

M3 - Conference contribution

AN - SCOPUS:78149451854

SN - 9781424463343

T3 - 3rd International Workshop on Advanced Computational Intelligence, IWACI 2010

SP - 522

EP - 526

BT - 3rd International Workshop on Advanced Computational Intelligence, IWACI 2010

T2 - 3rd International Workshop on Advanced Computational Intelligence, IWACI 2010

Y2 - 25 August 2010 through 27 August 2010

ER -

Segmentation of blood vessels in fundus color images by radon transform and morphological reconstruction

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this