UB ScholarWorks

Computer Vision and the Eye: Determining Intraocular Pressure from Frontal Eye Images

Show simple item record

dc.contributor.author Faezipour, Miad
dc.contributor.author Abuzneid, Abdelshakour
dc.contributor.author Aloudat, Mohammad
dc.contributor.author El-Sayed, Ahmed
dc.date.accessioned 2021-04-01T14:07:14Z
dc.date.available 2021-04-01T14:07:14Z
dc.date.issued 2021-04-09
dc.identifier.uri https://scholarworks.bridgeport.edu/xmlui/handle/123456789/4430
dc.description.abstract INTRODUCTION Glaucoma, the silent thief of vision, is mostly caused by the gradual increase of pressure in the eye which is known as Intraocular Pressure (IOP). An effective way to prevent the rise in eye pressure is by early detection Prior computer vision based work regarding IOP rely on fundus images of the optic nerves. OBJECTIVE This paper provides a novel computer vision based framework to help in the initial IOP screening using only frontal eye images. METHODS The framework first introduces the utilization of a fully convolutional network (FCN); as an instance of deep learning on frontal eye images for sclera and iris segmentation. Using these extracted areas, six features that include mean redness level (MRL) of the sclera, red area percentage (RAP), Pupil/Iris diameter ratio and three sclera contour features (distance, area and angle) are computed. RESULTS A database of images from the Princess Basma Hospital is used in this work, containing 400 facial images; 200 cases with normal IOP and 200 cases with high IOP. Once the features are extracted, two classifiers (support vector machine and decision tree) are applied to obtain the status of the patients in terms IOP (normal or high) The overall accuracy of the proposed framework is over 97 75 using decision tree. CONCLUSION The novelties and contributions of this work include introducing a fully convolutional network architecture for eye sclera segmentation, in addition to scientifically correlating the frontal eye view (image) with IOP by introducing new sclera contour features that have not been previously introduced in the literature from frontal eye images for IOP status determination. en_US
dc.language.iso en_US en_US
dc.subject Frontal eye image en_US
dc.subject Intraocular pressure en_US
dc.title Computer Vision and the Eye: Determining Intraocular Pressure from Frontal Eye Images en_US
dc.type Other en_US
dc.institute.department School of Engineering en_US
dc.institute.name University of Bridgeport en_US
dc.event.location Bridgeport, CT en_US
dc.event.name Faculty Research Day en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search ScholarWorks


Advanced Search

Browse

My Account