A morphologic three-stage approach for detecting exudates in color eye fundus images

Authors:
Daniel Welfer;Jacob Scharcanski;Diane Ruschel Marinho
Affiliations:
Universidade Federal do Rio, Porto Alegre, RS, Brasil;Universidade Federal do Rio, Porto Alegre, RS, Brasil;Universidade Federal do Rio, Porto Alegre, RS, Brasil
Venue:
Proceedings of the 2010 ACM Symposium on Applied Computing
Year:
2010

Citing 2
Cited 0

Morphological Image Analysis: Principles and Applications

Morphological Image Analysis: Principles and Applications
Comparative pixel-level exudate recognition in colour retinal images

ICIAR'05 Proceedings of the Second international conference on Image Analysis and Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

An efficient detection of exudate lesions in color eye fundus images is an essential stage for grading the Diabetic Macular Edema automatically. In this work, we present a new automatic method based on mathematical morphology to locate exudate lesions. The proposed method was evaluated using the publicly available DIARETDB1 database, and it obtains 72.21% of mean sensitivity and 98.97% of mean specificity. This results indicate that our approach potentially can achieve a better performance than other known methods proposed in the literature.