Polar run-length features in segmentation of retinal blood vessels

S. H. Rezatofighi; A. Roodaki; A. Pourmorteza; H. Soltanian-Zadeh

doi:10.1109/ICDIP.2009.18

Polar run-length features in segmentation of retinal blood vessels

S. H. Rezatofighi, A. Roodaki, A. Pourmorteza, H. Soltanian-Zadeh

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

2 Citations (Scopus)

Abstract

Manual segmentation of retinal blood vessels in optic fundus images is a tiresome task. Several methods have previously been proposed for the automatic segmentation of retinal blood vessels. In this paper we propose a classifierbased method. First the images are preprocessed so that the within class variability of the vessel and background classes are minimized. Next, the image is scanned with a window of a certain size. Polar run-length matrices are simply created by transforming the windows into polar coordinates and then constructing conventional run length matrices. Two features are then extracted for each gray level value in the polar run length matrix. The feature vectors are then classified using a multilayer perceptron artificial neural network. The performance of the proposed method is compared with that of the human observers and with those methods previously reported in literature.

Original language	English
Title of host publication	Proceedings - 2009 International Conference on Digital Image Processing, ICDIP 2009
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	72-75
Number of pages	4
ISBN (Print)	9780769535654
DOIs	https://doi.org/10.1109/ICDIP.2009.18
Publication status	Published - 4 Aug 2009
Externally published	Yes
Event	International Conference on Digital Image Processing (ICDIP) 2009 - Bangkok, Thailand Duration: 7 Mar 2009 → 9 Mar 2009 Conference number: 1st https://ieeexplore.ieee.org/xpl/conhome/5190501/proceeding (Proceedings)

Conference

Conference	International Conference on Digital Image Processing (ICDIP) 2009
Abbreviated title	ICDIP 2009
Country/Territory	Thailand
City	Bangkok
Period	7/03/09 → 9/03/09
Internet address	https://ieeexplore.ieee.org/xpl/conhome/5190501/proceeding (Proceedings)

Keywords

Artificial neural network
DoOG filters
Polar transformation
Retinal vessel segmentation
Run-length matrix

Access to Document

10.1109/ICDIP.2009.18

Cite this

@inproceedings{b0e9fde4603a4ce483cf17cf5c3fd116,

title = "Polar run-length features in segmentation of retinal blood vessels",

abstract = "Manual segmentation of retinal blood vessels in optic fundus images is a tiresome task. Several methods have previously been proposed for the automatic segmentation of retinal blood vessels. In this paper we propose a classifierbased method. First the images are preprocessed so that the within class variability of the vessel and background classes are minimized. Next, the image is scanned with a window of a certain size. Polar run-length matrices are simply created by transforming the windows into polar coordinates and then constructing conventional run length matrices. Two features are then extracted for each gray level value in the polar run length matrix. The feature vectors are then classified using a multilayer perceptron artificial neural network. The performance of the proposed method is compared with that of the human observers and with those methods previously reported in literature.",

keywords = "Artificial neural network, DoOG filters, Polar transformation, Retinal vessel segmentation, Run-length matrix",

author = "Rezatofighi, {S. H.} and A. Roodaki and A. Pourmorteza and H. Soltanian-Zadeh",

year = "2009",

month = aug,

day = "4",

doi = "10.1109/ICDIP.2009.18",

language = "English",

isbn = "9780769535654",

pages = "72--75",

booktitle = "Proceedings - 2009 International Conference on Digital Image Processing, ICDIP 2009",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "International Conference on Digital Image Processing (ICDIP) 2009, ICDIP 2009 ; Conference date: 07-03-2009 Through 09-03-2009",

url = "https://ieeexplore.ieee.org/xpl/conhome/5190501/proceeding",

}

Rezatofighi, SH, Roodaki, A, Pourmorteza, A & Soltanian-Zadeh, H 2009, Polar run-length features in segmentation of retinal blood vessels. in Proceedings - 2009 International Conference on Digital Image Processing, ICDIP 2009. IEEE, Institute of Electrical and Electronics Engineers, pp. 72-75, International Conference on Digital Image Processing (ICDIP) 2009, Bangkok, Thailand, 7/03/09. https://doi.org/10.1109/ICDIP.2009.18

Polar run-length features in segmentation of retinal blood vessels. / Rezatofighi, S. H.; Roodaki, A.; Pourmorteza, A. et al.
Proceedings - 2009 International Conference on Digital Image Processing, ICDIP 2009. IEEE, Institute of Electrical and Electronics Engineers, 2009. p. 72-75.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Polar run-length features in segmentation of retinal blood vessels

AU - Rezatofighi, S. H.

AU - Roodaki, A.

AU - Pourmorteza, A.

AU - Soltanian-Zadeh, H.

N1 - Conference code: 1st

PY - 2009/8/4

Y1 - 2009/8/4

N2 - Manual segmentation of retinal blood vessels in optic fundus images is a tiresome task. Several methods have previously been proposed for the automatic segmentation of retinal blood vessels. In this paper we propose a classifierbased method. First the images are preprocessed so that the within class variability of the vessel and background classes are minimized. Next, the image is scanned with a window of a certain size. Polar run-length matrices are simply created by transforming the windows into polar coordinates and then constructing conventional run length matrices. Two features are then extracted for each gray level value in the polar run length matrix. The feature vectors are then classified using a multilayer perceptron artificial neural network. The performance of the proposed method is compared with that of the human observers and with those methods previously reported in literature.

AB - Manual segmentation of retinal blood vessels in optic fundus images is a tiresome task. Several methods have previously been proposed for the automatic segmentation of retinal blood vessels. In this paper we propose a classifierbased method. First the images are preprocessed so that the within class variability of the vessel and background classes are minimized. Next, the image is scanned with a window of a certain size. Polar run-length matrices are simply created by transforming the windows into polar coordinates and then constructing conventional run length matrices. Two features are then extracted for each gray level value in the polar run length matrix. The feature vectors are then classified using a multilayer perceptron artificial neural network. The performance of the proposed method is compared with that of the human observers and with those methods previously reported in literature.

KW - Artificial neural network

KW - DoOG filters

KW - Polar transformation

KW - Retinal vessel segmentation

KW - Run-length matrix

UR - http://www.scopus.com/inward/record.url?scp=70449331699&partnerID=8YFLogxK

U2 - 10.1109/ICDIP.2009.18

DO - 10.1109/ICDIP.2009.18

M3 - Conference Paper

AN - SCOPUS:70449331699

SN - 9780769535654

SP - 72

EP - 75

BT - Proceedings - 2009 International Conference on Digital Image Processing, ICDIP 2009

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - International Conference on Digital Image Processing (ICDIP) 2009

Y2 - 7 March 2009 through 9 March 2009

ER -

Polar run-length features in segmentation of retinal blood vessels

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this