Detection of Retinal Blood Vessels Based on Morphological Analysis with Multiscale Structure Elements and SVM Classification

Pil Un KIM; Yunjung LEE; Sanghyo WOO; Chulho WON; Jin Ho CHO; Myoung Nam KIM

doi:10.1587/transinf.E94.D.1519

Detection of Retinal Blood Vessels Based on Morphological Analysis with Multiscale Structure Elements and SVM Classification

Pil Un KIM, Yunjung LEE, Sanghyo WOO, Chulho WON, Jin Ho CHO, Myoung Nam KIM

Full Text Views

0

Share
Cite this

Summary :

Since retina blood vessels (RBV) are a major factor in ophthalmological diagnosis, it is essential to detect RBV from a fundus image. In this letter, we proposed the detection method of RBV using a morphological analysis and support vector machine classification. The proposed RBV detection method consists of three strategies: pre-processing, features extraction and classification. In pre-processing, noises were reduced and RBV were enhanced by anisotropic diffusion filtering and illumination equalization. Features were extracted by using the image intensity and morphology of RBV. And a support vector machine (SVM) classification algorithm was used to detect RBV. The proposed RBV detection method was simulated and validated by using the DRIVE database. The averages of accuracy and TPR are 0.94 and 0.78, respectively. Moreover, by comparison, we confirmed that the proposed RBV detection method detected RBV better than the recent RBV detections methods.

Publication: IEICE TRANSACTIONS on Information Vol.E94-D No.7 pp.1519-1522

Publication Date: 2011/07/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E94.D.1519

Type of Manuscript: LETTER

Category: Biological Engineering

Cite this

Copy

Pil Un KIM, Yunjung LEE, Sanghyo WOO, Chulho WON, Jin Ho CHO, Myoung Nam KIM, "Detection of Retinal Blood Vessels Based on Morphological Analysis with Multiscale Structure Elements and SVM Classification" in IEICE TRANSACTIONS on Information, vol. E94-D, no. 7, pp. 1519-1522, July 2011, doi: 10.1587/transinf.E94.D.1519.
Abstract: Since retina blood vessels (RBV) are a major factor in ophthalmological diagnosis, it is essential to detect RBV from a fundus image. In this letter, we proposed the detection method of RBV using a morphological analysis and support vector machine classification. The proposed RBV detection method consists of three strategies: pre-processing, features extraction and classification. In pre-processing, noises were reduced and RBV were enhanced by anisotropic diffusion filtering and illumination equalization. Features were extracted by using the image intensity and morphology of RBV. And a support vector machine (SVM) classification algorithm was used to detect RBV. The proposed RBV detection method was simulated and validated by using the DRIVE database. The averages of accuracy and TPR are 0.94 and 0.78, respectively. Moreover, by comparison, we confirmed that the proposed RBV detection method detected RBV better than the recent RBV detections methods.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E94.D.1519/_p

Copy

@ARTICLE{e94-d_7_1519,
author={Pil Un KIM, Yunjung LEE, Sanghyo WOO, Chulho WON, Jin Ho CHO, Myoung Nam KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Detection of Retinal Blood Vessels Based on Morphological Analysis with Multiscale Structure Elements and SVM Classification},
year={2011},
volume={E94-D},
number={7},
pages={1519-1522},
abstract={Since retina blood vessels (RBV) are a major factor in ophthalmological diagnosis, it is essential to detect RBV from a fundus image. In this letter, we proposed the detection method of RBV using a morphological analysis and support vector machine classification. The proposed RBV detection method consists of three strategies: pre-processing, features extraction and classification. In pre-processing, noises were reduced and RBV were enhanced by anisotropic diffusion filtering and illumination equalization. Features were extracted by using the image intensity and morphology of RBV. And a support vector machine (SVM) classification algorithm was used to detect RBV. The proposed RBV detection method was simulated and validated by using the DRIVE database. The averages of accuracy and TPR are 0.94 and 0.78, respectively. Moreover, by comparison, we confirmed that the proposed RBV detection method detected RBV better than the recent RBV detections methods.},
keywords={},
doi={10.1587/transinf.E94.D.1519},
ISSN={1745-1361},
month={July},}

Copy

TY - JOUR
TI - Detection of Retinal Blood Vessels Based on Morphological Analysis with Multiscale Structure Elements and SVM Classification
T2 - IEICE TRANSACTIONS on Information
SP - 1519
EP - 1522
AU - Pil Un KIM
AU - Yunjung LEE
AU - Sanghyo WOO
AU - Chulho WON
AU - Jin Ho CHO
AU - Myoung Nam KIM
PY - 2011
DO - 10.1587/transinf.E94.D.1519
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2011
AB - Since retina blood vessels (RBV) are a major factor in ophthalmological diagnosis, it is essential to detect RBV from a fundus image. In this letter, we proposed the detection method of RBV using a morphological analysis and support vector machine classification. The proposed RBV detection method consists of three strategies: pre-processing, features extraction and classification. In pre-processing, noises were reduced and RBV were enhanced by anisotropic diffusion filtering and illumination equalization. Features were extracted by using the image intensity and morphology of RBV. And a support vector machine (SVM) classification algorithm was used to detect RBV. The proposed RBV detection method was simulated and validated by using the DRIVE database. The averages of accuracy and TPR are 0.94 and 0.78, respectively. Moreover, by comparison, we confirmed that the proposed RBV detection method detected RBV better than the recent RBV detections methods.
ER -