期刊名称：International Journal of Electronics and Computer Science Engineering
电子版ISSN：2277-1956
出版年度：2013
卷号：2
期号：3
页码：963-971
出版社：Buldanshahr : IJECSE
摘要：Diabetic Retinopathy (DR) is one of the chronic diseases which has caused disturbance in the medical world, initial symptoms are difficult to detect and predict, moreover if problem does not get noticed and not cured properly then may lead to permanent blindness. So the urge arises for quick and relevant systems which can find whether the patient is suffering from DR or not. In automatic detection of lesion in eye due to diabetic retinopathy the lesions are found based upon the lesion’s characteristic for e.g. exudates are bright spots whereas haemorrhages are dark lesions. The detection of lesions facilitates in initial step of the disease, with this we can perform automatic screening of images whether they are DR infected or not. In this system with the help of morphological image processing methods, we are trying to find lesions in two categories i.e. dark and bright lesions. The present system is able to detect 90 % exudates in image and 85% dark lesions.
