TY - JOUR AU - Kaur, Jaskirat AU - Mittal, Deepti PY - 2015/03/01 Y2 - 2024/03/29 TI - Segmentation and Measurement of Exudates in Fundus Images of the Retina for Detection of Retinal Disease JF - British Journal of Healthcare and Medical Research JA - BJHMR VL - 2 IS - 1 SE - Original Articles DO - 10.14738/jbemi.21.987 UR - https://journals.scholarpublishing.org/index.php/JBEMi/article/view/987 SP - 27 AB - <p><span style="line-height: 115%; font-family: 'Calibri','sans-serif'; font-size: 11pt; mso-bidi-font-size: 12.0pt; mso-fareast-font-family: SimSun; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;"><span style="line-height: 115%; font-family: 'Calibri','sans-serif'; font-size: 11pt; mso-bidi-font-size: 12.0pt; mso-fareast-font-family: SimSun; mso-bidi-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;">Retinal diseases are asymptomatic in nature with the significant effect of vision loss. With the growing number of retinopathy cases each year there is a requirement of the evaluation of large amount of database. This has led to the development of numerous automated and semi automated evaluation methods to track the retinal diseases. In this study, a simpler automated method is developed to diagnose retinal disease as far as exudates are concerned. Previously used segmentation methods do not generate very satisfactory results mainly because the composition of exudates which are degenerated regions in retinal fundus image is non homogeneous. Therefore an alternative method for segmentation is developed to use the homogeneity of healthy regions than degenerated regions. The developed technique initially separates the healthy regions like blood vessels and optic disc from the retinal fundus images and classifies as healthy. Further the dynamic region growing method is employed for the segmentation of exudates in the images containing diabetic retinal disease. The technique developed is examined on various retinal images and the outcomes reveal that the presented technique performs better than the previous proposed methods for the segmentation of exudates.</span></span></p> ER -