Automatic Optic Disc Boundary Extraction Based on Saliency Object Detection and Modified Local Intensity Clustering Model in Retinal Images

Wei ZHOU; Chengdong WU; Yuan GAO; Xiaosheng YU

doi:10.1587/transfun.E100.A.2069

Automatic Optic Disc Boundary Extraction Based on Saliency Object Detection and Modified Local Intensity Clustering Model in Retinal Images

Wei ZHOU, Chengdong WU, Yuan GAO, Xiaosheng YU

Full Text Views

0

Share
Cite this

Summary :

Accurate optic disc localization and segmentation are two main steps when designing automated screening systems for diabetic retinopathy. In this paper, a novel optic disc detection approach based on saliency object detection and modified local intensity clustering model is proposed. It consists of two stages: in the first stage, the saliency detection technique is introduced to the enhanced retinal image with the aim of locating the optic disc. In the second stage, the optic disc boundary is extracted by the modified Local Intensity Clustering (LIC) model with oval-shaped constrain. The performance of our proposed approach is tested on the public DIARETDB1 database. Compared to the state-of-the-art approaches, the experimental results show the advantages and effectiveness of the proposed approach.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E100-A No.9 pp.2069-2072

Publication Date: 2017/09/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E100.A.2069

Type of Manuscript: LETTER

Category: Image

Authors

Wei ZHOU
  Northeastern University
Chengdong WU
  Northeastern University
Yuan GAO
  Northeastern University
Xiaosheng YU
  Northeastern University

Keyword

optic disc segmentation, saliency detection, LIC, shape prior information

Cite this

Copy

Wei ZHOU, Chengdong WU, Yuan GAO, Xiaosheng YU, "Automatic Optic Disc Boundary Extraction Based on Saliency Object Detection and Modified Local Intensity Clustering Model in Retinal Images" in IEICE TRANSACTIONS on Fundamentals, vol. E100-A, no. 9, pp. 2069-2072, September 2017, doi: 10.1587/transfun.E100.A.2069.
Abstract: Accurate optic disc localization and segmentation are two main steps when designing automated screening systems for diabetic retinopathy. In this paper, a novel optic disc detection approach based on saliency object detection and modified local intensity clustering model is proposed. It consists of two stages: in the first stage, the saliency detection technique is introduced to the enhanced retinal image with the aim of locating the optic disc. In the second stage, the optic disc boundary is extracted by the modified Local Intensity Clustering (LIC) model with oval-shaped constrain. The performance of our proposed approach is tested on the public DIARETDB1 database. Compared to the state-of-the-art approaches, the experimental results show the advantages and effectiveness of the proposed approach.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E100.A.2069/_p

Copy

@ARTICLE{e100-a_9_2069,
author={Wei ZHOU, Chengdong WU, Yuan GAO, Xiaosheng YU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Automatic Optic Disc Boundary Extraction Based on Saliency Object Detection and Modified Local Intensity Clustering Model in Retinal Images},
year={2017},
volume={E100-A},
number={9},
pages={2069-2072},
abstract={Accurate optic disc localization and segmentation are two main steps when designing automated screening systems for diabetic retinopathy. In this paper, a novel optic disc detection approach based on saliency object detection and modified local intensity clustering model is proposed. It consists of two stages: in the first stage, the saliency detection technique is introduced to the enhanced retinal image with the aim of locating the optic disc. In the second stage, the optic disc boundary is extracted by the modified Local Intensity Clustering (LIC) model with oval-shaped constrain. The performance of our proposed approach is tested on the public DIARETDB1 database. Compared to the state-of-the-art approaches, the experimental results show the advantages and effectiveness of the proposed approach.},
keywords={},
doi={10.1587/transfun.E100.A.2069},
ISSN={1745-1337},
month={September},}

Copy

TY - JOUR
TI - Automatic Optic Disc Boundary Extraction Based on Saliency Object Detection and Modified Local Intensity Clustering Model in Retinal Images
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2069
EP - 2072
AU - Wei ZHOU
AU - Chengdong WU
AU - Yuan GAO
AU - Xiaosheng YU
PY - 2017
DO - 10.1587/transfun.E100.A.2069
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E100-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2017
AB - Accurate optic disc localization and segmentation are two main steps when designing automated screening systems for diabetic retinopathy. In this paper, a novel optic disc detection approach based on saliency object detection and modified local intensity clustering model is proposed. It consists of two stages: in the first stage, the saliency detection technique is introduced to the enhanced retinal image with the aim of locating the optic disc. In the second stage, the optic disc boundary is extracted by the modified Local Intensity Clustering (LIC) model with oval-shaped constrain. The performance of our proposed approach is tested on the public DIARETDB1 database. Compared to the state-of-the-art approaches, the experimental results show the advantages and effectiveness of the proposed approach.
ER -