Title :
Improving iris segmentation by specular reflections removable
Author :
Yahya, Abdulsamad Ebrahim ; Nordin, Md Jan
Author_Institution :
Fac. of Inf. Sci. & Technol., Nat. Univ. of Malaysia, Bangi, Malaysia
Abstract :
Iris segmentation is one of the most important steps in iris recognition system and determines the accuracy of matching. This paper proposes a new specular reflection removable method for accurate iris segmentation of in iris. The procedure includes two steps: sepcular reflection detection and image inpainting. Experimental results show that the technique has a good performance, which improve the accuracy on iris segmentation.
Keywords :
image matching; image segmentation; iris recognition; image inpainting; image matching; iris recognition system; iris segmentation; specular reflection removable method; Eyelashes; Eyelids; Image segmentation; Iris recognition; Pixel; Reflection; Transforms; image inpainting; iris segmentation; reflection removal;
Conference_Titel :
Information Technology (ITSim), 2010 International Symposium in
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4244-6715-0
DOI :
10.1109/ITSIM.2010.5561293
