-
117
pages
-
English
-
Documents
-
2010
Description
VILNIUS UNIVERSITYJustas KranauskasPERSON IDENTIFICATION BY FACE AND IRISDoctoral DissertationPhysical Sciences, Informatics (09 P)Vilnius, 2010Doctoral dissertation was prepared at Vilnius University in 2005-2009.Scientific SupervisorAssoc. Prof. Dr. Algirdas Bastys (Vilnius University, Physical Sciences,Informatics - 09 P)AbstractIn this thesis, person identification by combining automatic face and irisrecognition is analyzed. Person identification by his face is one of the mostintuitive from all biometric measures. We are used to recognizing familiarfaces and confirming identity by a short glance at one’s id card which con-tains image of the face. We are also used to being observed by surveillancecameras, which can perform biometric authentication without even beingnoticed. However, facial biometrics is one of most unstable metrics becausethe face gets noticeably older in several years and can frequently changedepending on the mood of its owner. The core algorithm for facial recog-nition presented in this work is based on Gabor features. Deep analysis ofeach step helped to develop the method with better or similar accuracy tothe best published results received on the same datasets, while being simpleand fast.On the other hand, person identification by his iris is one of the mostsophisticated, stable and accurate biometrics.
-
Publié par
-
Publié le
01 janvier 2010
-
Langue
English
-
Poids de l'ouvrage
4 Mo