DSpace@nitr >
National Institue of Technology- Rourkela >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/956

Full metadata record

DC FieldValueLanguage
contributor.authorMehrotra, H-
contributor.authorBadrinath, G S-
contributor.authorMajhi, B-
contributor.authorGupta, P-
date.accessioned2009-07-30T02:27:04Z-
date.available2009-07-30T02:27:04Z-
date.issued2009-
identifier.citationIEEE Workshop on Computational Intelligence in Biometrics: Theory, Algorithms, and Applications, 2009. CIB 2009, Nashville, TN, March 30 2009-April 2 2009 Page(s):59 - 62en
identifier.urihttp://dx.doi.org/10.1109/CIB.2009.4925687-
identifier.urihttp://hdl.handle.net/2080/956-
description.abstractThis paper proposes a novel feature extraction and matching technique for iris recognition using interest points. The feature set comprises of spatial location of corner points and entropy information of the window around the corner. Corner matching is an elementary problem that is resolved using dual stage approach. At first stage the potential corners are obtained by finding Euclidean distance between spatial coordinates. These potential corners are used to find actual corners based on their affinity around a window, which is measured using mutual information (MI). For the purpose of evaluating experimental results three different datasets i.e., BATH, CASIA and IITK are used. The proposed dual stage approach has accuracy more than 98% with FRR of 0.0% and FAR of 2.61%.en
format.extent510984 bytes-
format.mimetypeapplication/pdf-
language.isoen-
publisherIEEEen
subjectbiometrics (access control)en
subjectfeature extractionen
subjectimage matchingen
subjectimage recognitionen
titleAn Efficient Dual Stage Approach for Iris Feature Extraction Using Interest Point Pairingen
typeArticleen
Appears in Collections:Conference Papers

Files in This Item:

File Description SizeFormat
majhi.pdf499KbAdobe PDFView/Open

Show simple item record

All items in DSpace are protected by copyright, with all rights reserved.

 

Powered by DSpace Feedback