Abstract:
Authentication is the process of identifying someone or something and
verifying its validity.There are a lot biometric technologies, which include finger
scanning, finger vein ID, facial recognition, voice recognition, retina scanning, iris
recognition etc. Being one of the most reliable methods, we have chosen to analyze iris
recognition. Since it is unique, unchangeable and difficult to falsify, it is considered to
be a great candidate for authentication. This process involves several steps –
segmentation, normalization, encoding, matching. The quality of iris pictures
noninheritable at-a-distance or below less strained imaging environments is understood
to degrade the iris recognition accuracy. The periocular data is inherently embedded in
such iris pictures and might be exploited to help within the iris recognition below such
non-ideal situations. Our main aims in this thesis are new methods for the segmentation
and encoding stages of the iris recognition using trapezoidal templates. Considering all
the newly presented methods, we can say that they improve the performance of the
algorithm for the CASIA database.
