Detection of red lesions in digital fundus images

Authors:
Giri Babu Kande;T. Satya Savithri;P. Venkata Subbaiah;M. R. N. Tagore
Affiliations:
Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, India;Jawaharlal Nehru Technological University, Hyderabad, India;Amrita Sai Institute of Science & Technology, Paritala, India;Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, India
Venue:
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Year:
2009

Citing 3
Cited 1

An image-processing strategy for the segmentation and quantification of microaneurysms in fluorescein angiograms of the ocular fundus

Computers and Biomedical Research
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Automatic Detection of Microaneurysms in Color Fundus Images of the Human Retina by Means of the Bounding Box Closing

ISMDA '02 Proceedings of the Third International Symposium on Medical Data Analysis

Sparse Representation Classifier for microaneurysm detection and retinal blood vessel extraction

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an efficient approach for automatic detection of red lesions in ocular fundus images. The approach uses the intensity information from red and green channels of the same retinal image to correct non-uniform illumination in color fundus images. Matched filtering is utilized to enhance the contrast of red lesions against the background. The enhanced red lesions are than segmented by employing relative entropy based thresholding which can well maintain the spatial structure of the red lesion segments. Then morphological top-hat transformation is used to suppress the enhanced vasculature. SVMs are used to classify the candidate red lesions from other dark segments. Experimental evaluation of the proposed approach demonstrates superior performance over other red lesion detection algorithms recently reported in the literature.