1. Digital Repository
  2. Computing and Technology
  3. Symposia and Conferences
  4. International Conference on Advances in Computing and Technology (ICACT)
  5. KICACT 2016
Please use this identifier to cite or link to this item: http://repository.kln.ac.lk/handle/123456789/15648
Full metadata record
DC FieldValueLanguage
dc.contributor.authorYuan-Tsung Chang-
dc.contributor.authorChih-Wen Ou-
dc.contributor.authorJayasekara, J.M.N.D.B.-
dc.contributor.authorYung-Hui Li-
dc.date.accessioned2016-12-23T08:45:16Z-
dc.date.available2016-12-23T08:45:16Z-
dc.date.issued2016-
dc.identifier.citationYuan-Tsung Chang, Chih-Wen Ou, Jayasekara, J.M.N.D.B. and Yung-Hui Li 2016. Performing Iris Segmentation by Using Geodesic Active Contour (GAC). Kelaniya International Conference on Advances in Computing and Technology (KICACT - 2016), Faculty of Computing and Technology, University of Kelaniya, Sri Lanka. p 75.en_US
dc.identifier.isbn978-955-704-013-4-
dc.identifier.urihttp://repository.kln.ac.lk/handle/123456789/15648-
dc.description.abstractA novel iris segmentation technique based on active contour is proposed in this paper. Our approach includes two important issues, pupil segmentation and iris circle calculation. If the correct center position and radius of pupil can be find out in tested image, then the iris in the result will be able to precisely segment. The final accuracy for ICE dataset is reached around 92%, and also can get high accuracy 79% for UBIRIS. Our results demonstrate that the proposed iris segmentation can perform well with high accuracy for Iris’s image.en_US
dc.language.isoenen_US
dc.publisherFaculty of Computing and Technology, University of Kelaniya, Sri Lankaen_US
dc.subjectGACen_US
dc.subjectIris Segmentationen_US
dc.subjectICEen_US
dc.subjectUBIRISen_US
dc.titlePerforming Iris Segmentation by Using Geodesic Active Contour (GAC)en_US
dc.typeArticleen_US
Appears in Collections:KICACT 2016

Files in This Item:
File Description SizeFormat 
75.pdf116.32 kBAdobe PDFView/Open
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.