Iris Database Classification and Indexing

Joseph, Jobin (2011) Iris Database Classification and Indexing. MTech thesis.



For increasing threat to the security systems biometric has been using widely for many applications. Biometric recognition is the recognition of individuals based in
their physiological or behavioral characteristics.Examples of biometrics are face, iris, fingerprints, voice, palms, hand geometry, retina, handwriting, gait etc. The performance of the biometric system depends on the search time and the error rate. these two factors are depends upon the size of the database. So here proposing one method to index the database within minimum time and search
the minimum area of the database.The error rates of a biometric identification system are dramatically increasing with the size of database.Here used a method to index the iris data base using dct and the reordering of the DCT coefficents.Here proposed three new methods to extract the features from the iris strip.Among the three partitioning method discussing the efficient searching method the 10x10
square windowing gives a penetration rate of 9.8 percentage L-slicing method given penetration rate of 5.5 and the 8x8 slicing has given a penetration rate of .2 percentage of the total database,.In this the experiment has been done on CASIA Iris database.

Item Type:Thesis (MTech)
Uncontrolled Keywords:DCT, square windowing, L-slice,8x8 slice
Subjects:Engineering and Technology > Computer and Information Science > Information Security
Divisions: Engineering and Technology > Department of Computer Science
ID Code:2771
Deposited By:Mr JOBIN JOSEPH
Deposited On:03 Jun 2011 17:44
Last Modified:14 Jun 2012 15:16
Related URLs:
Supervisor(s):Sa, P K

Repository Staff Only: item control page