A model-based approach for automated feature extraction in fundus images

Huiqi Li; Opas Chutatape

doi:10.1109/iccv.2003.1238371

A model-based approach for automated feature extraction in fundus images

Huiqi Li^*, Opas Chutatape

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

132 Citations (Scopus)

Abstract

A new approach to automatically extract the main features in color fundus images are proposed in this paper. Optic disk is localized by the principal component analysis (PCA) and its shape is detected by a modified active shape model (ASM). Exudates are extracted by the combined region growing and edge detection, A fundus coordinate system is further set up based on the fovea localization to provide a better description of the features in fundus images. The success rates achieved are 99%, 94%, and 100% for disk localization, disk boundary detection, and fovea localization respectively. The sensitivity and specificity for exudate detection are 100% and 71%. The success of the proposed algorithms can be attributed to the utilization of the model-based methods.

Original language	English
Pages	394-399
Number of pages	6
DOIs	https://doi.org/10.1109/iccv.2003.1238371
Publication status	Published - 2003
Externally published	Yes
Event	Proceedings: Ninth IEEE International Conference on Computer Vision - Nice, France Duration: 13 Oct 2003 → 16 Oct 2003

Conference

Conference	Proceedings: Ninth IEEE International Conference on Computer Vision
Country/Territory	France
City	Nice
Period	13/10/03 → 16/10/03

Access to Document

10.1109/iccv.2003.1238371

Cite this

@conference{db4b43ec5c6a438c8f48f85dd8b9661e,

title = "A model-based approach for automated feature extraction in fundus images",

abstract = "A new approach to automatically extract the main features in color fundus images are proposed in this paper. Optic disk is localized by the principal component analysis (PCA) and its shape is detected by a modified active shape model (ASM). Exudates are extracted by the combined region growing and edge detection, A fundus coordinate system is further set up based on the fovea localization to provide a better description of the features in fundus images. The success rates achieved are 99%, 94%, and 100% for disk localization, disk boundary detection, and fovea localization respectively. The sensitivity and specificity for exudate detection are 100% and 71%. The success of the proposed algorithms can be attributed to the utilization of the model-based methods.",

author = "Huiqi Li and Opas Chutatape",

year = "2003",

doi = "10.1109/iccv.2003.1238371",

language = "English",

pages = "394--399",

note = "Proceedings: Ninth IEEE International Conference on Computer Vision ; Conference date: 13-10-2003 Through 16-10-2003",

}

TY - CONF

T1 - A model-based approach for automated feature extraction in fundus images

AU - Li, Huiqi

AU - Chutatape, Opas

PY - 2003

Y1 - 2003

N2 - A new approach to automatically extract the main features in color fundus images are proposed in this paper. Optic disk is localized by the principal component analysis (PCA) and its shape is detected by a modified active shape model (ASM). Exudates are extracted by the combined region growing and edge detection, A fundus coordinate system is further set up based on the fovea localization to provide a better description of the features in fundus images. The success rates achieved are 99%, 94%, and 100% for disk localization, disk boundary detection, and fovea localization respectively. The sensitivity and specificity for exudate detection are 100% and 71%. The success of the proposed algorithms can be attributed to the utilization of the model-based methods.

AB - A new approach to automatically extract the main features in color fundus images are proposed in this paper. Optic disk is localized by the principal component analysis (PCA) and its shape is detected by a modified active shape model (ASM). Exudates are extracted by the combined region growing and edge detection, A fundus coordinate system is further set up based on the fovea localization to provide a better description of the features in fundus images. The success rates achieved are 99%, 94%, and 100% for disk localization, disk boundary detection, and fovea localization respectively. The sensitivity and specificity for exudate detection are 100% and 71%. The success of the proposed algorithms can be attributed to the utilization of the model-based methods.

UR - http://www.scopus.com/inward/record.url?scp=0344551879&partnerID=8YFLogxK

U2 - 10.1109/iccv.2003.1238371

DO - 10.1109/iccv.2003.1238371

M3 - Paper

AN - SCOPUS:0344551879

SP - 394

EP - 399

T2 - Proceedings: Ninth IEEE International Conference on Computer Vision

Y2 - 13 October 2003 through 16 October 2003

ER -

A model-based approach for automated feature extraction in fundus images

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this