Open AccessIdentification of Hemorrhages in Iris Using Hybrid Morphological Method
Author(s) -
Robbi Rahim
Publication year - 2020
Publication title -
international journal on recent and innovation trends in computing and communication
Language(s) - English
Resource type - Journals
ISSN - 2321-8169
DOI - 10.17762/ijritcc.v8i3.5422
Subject(s) - thresholding , fundus (uterus) , computer science , artificial intelligence , medicine , computer vision , diabetic retinopathy , vitreous hemorrhage , iris (biosensor) , blood vessel , subtraction , ophthalmology , image (mathematics) , pattern recognition (psychology) , biometrics , diabetes mellitus , mathematics , arithmetic , endocrinology
In the field of ophthalmology, hemorrhage is the term used more often because of increasing diabetic patients. It’s a challenge amidst the ophthalmologist to distinguish the hemorrhage from the blood vessels, these lands in various problems. In the past various techniques were employed for the detection of the hemorrhage but they were not so accurate and often encountered misclassification between hemorrhage and blood vessels. Precise detection and classification of hemorrhage and blood vessel is very important in the diagnosis of many problems. This paper depicts a mechanized procedure for recognizing hemorrhages in fundus pictures. The acknowledgment of hemorrhages is one of the critical factors in the early finish of diabetic retinopathy. The algorithm proceeds through several steps such as image enhancement, image subtraction, morphological operations such as image thresholding, image strengthening, image thinning, erosion, morphological closing, image complement to suppress blood vessels and to highlight the hemorrhages