Features based classification of hard exudates in retinal images

• Published in: 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI) pp. 1652 - 1655
• Main Authors: Deshmukh, Anup V., Patil, Tejas G., Patankar, Sanika S., Kulkarni, Jayant V.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2015
• Subjects: Accuracy; Biomedical imaging; Diabetes; diabetic retinopathy; Entropy; exudates segmentation; Image segmentation; optic disk segmentation; Optical imaging; region growing; Retina; retinal fundus images
• ISBN: 9781479987900; 1479987905
• DOI: 10.1109/ICACCI.2015.7275850

Diabetes mellitus is a major disease spread all across the globe. Long-time diabetes mellitus causes the complication in the retina called Diabetic Retinopathy (DR), which results in visual loss and sometimes blindness. In this paper, we discuss a simple and effective algorithm for segmentation of the optic disk (OD) and bright lesions such as hard exudates from color retinal images. Color fundus images are enhanced using brightness transform function. Morphological operator along with the Circular Hough Transform (CHT) is used for optic disk segmentation. Further, local mean and entropy based region growing technique is applied in order to classify exudate - non-exudate pixels in retinal images. The performance of the proposed algorithm has been tested on publicly available standard Messidor database images with varied disease levels and non-uniform illumination. Experimentation yields 94% success rate for localization of the optic disk, 99% accuracy of classification of exudate - non-exudate pixels and subject level accuracy is found to be 93% and 67% in identifying the abnormal (with exudates) and normal (without exudates) images respectively.