Iris Database Classification and Indexing
Jobin Joseph · 2011
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.