{"title":"Three Sigma and Multilevel Active Contour Approach to Detect Optic Disc and Optic Cup","authors":"N. C. Patil, P. V. Rao","doi":"10.1109/ICATIECE45860.2019.9063813","DOIUrl":null,"url":null,"abstract":"One of the key factors to be looked at during design of an automated eye screening system is to find the optic disc and optic cup. Objective: In eye screening of diabetic patients, the feature such as hard exudates and cotton wool spots can be noticed which share similar properties with optic disc In certain diseases like glaucoma ophthalmologist look at the ratio of optic cup with optic disc to detect the presence or absence of glaucoma Currently, the process is manual performed by ophthalmologist, which a time consuming and tedious job. This fact motivated to design a fully automated procedure to detect optic cup and optic disc. Method: In the current paper a multilevel active contour technique is used that generates the snake to detect boundaries of optic cup and optic disc using intensity of the border pixels which are tested using 3σ control limits. The algorithm works in two parts. In part-1, optic disc boundary is detected and in part-2, the optic cup is marked by concentrating inside the area marked as optic disc in part-1. Findings: This approach reduces processing area and hence improves computational time A local database to carry out this work was created by collecting images from Karnataka Institute of Diabetology, Bangalore The results obtained by the proposed procedure are encouraging and have yielded 100% results with the fundus images containing full optic disc Improvement: The method is fully automatic and no user intervention is required","PeriodicalId":106496,"journal":{"name":"2019 1st International Conference on Advanced Technologies in Intelligent Control, Environment, Computing & Communication Engineering (ICATIECE)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 1st International Conference on Advanced Technologies in Intelligent Control, Environment, Computing & Communication Engineering (ICATIECE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICATIECE45860.2019.9063813","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
One of the key factors to be looked at during design of an automated eye screening system is to find the optic disc and optic cup. Objective: In eye screening of diabetic patients, the feature such as hard exudates and cotton wool spots can be noticed which share similar properties with optic disc In certain diseases like glaucoma ophthalmologist look at the ratio of optic cup with optic disc to detect the presence or absence of glaucoma Currently, the process is manual performed by ophthalmologist, which a time consuming and tedious job. This fact motivated to design a fully automated procedure to detect optic cup and optic disc. Method: In the current paper a multilevel active contour technique is used that generates the snake to detect boundaries of optic cup and optic disc using intensity of the border pixels which are tested using 3σ control limits. The algorithm works in two parts. In part-1, optic disc boundary is detected and in part-2, the optic cup is marked by concentrating inside the area marked as optic disc in part-1. Findings: This approach reduces processing area and hence improves computational time A local database to carry out this work was created by collecting images from Karnataka Institute of Diabetology, Bangalore The results obtained by the proposed procedure are encouraging and have yielded 100% results with the fundus images containing full optic disc Improvement: The method is fully automatic and no user intervention is required