Abstract
Many eye diseases such as Diabetic Retinopathy, Cataract, Glaucoma have their symptoms shown in the retina. To detect such diseases, the normal and abnormal retina should be differentiated. The Optic disc has been a prominent landmark for finding abnormalities in the retina. In this paper, we attempted two methods to localize the optic disc using the segmentation which is done on the interference map that is obtained from a family of generalized motion patterns of the image. In brief, we are adding motion to the image so that the bright regions can be extracted well by improving the contrast between the object and its background in the image. Then, the region of interest has been taken and binary image has been generated. In the 1st method, by thresholding, the optic disc has been segmented and its centre has been found. In the second method, the grab cut is used for segmentation. Both of our methods show better results when compared with the competing method.
Highlights
KEYWORDS Thresholding; segmentation; optic disc; optic disc centre; grabcut; graph cut Diabetic Retinopathy and Glaucoma are the most common diseases related to the retina
(5) The ROI is given as input to the grab cut algorithm (6) Binary image IOD is obtained as output of grab cut which contains a single candidate region
The proposed method 1 gives good results in terms of efficiency and less time consuming compared to the competing method, its performance reduces in the case of irregularly illuminated images
Summary
Diabetic Retinopathy and Glaucoma are the most common diseases related to the retina. For the automated detection of the abnormality, the detection of the optic disc and macula assist us to get vital information. Many methods have been discussed in the literature for finding the optic disc by observing the intensity and geometrical features. The first method is an extension to [1] which uses Interference map introduced in [2] to segment the optic disc. The second method uses the graph cut method by using the prior information obtained from the [1] method (Figure 22). This graph cut based method has given even better results compared to the first method. We present a literature survey, give a rundown about the method we adopted and discuss the novelty we brought, followed by experimental study and conclusion
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
