A Novel Fingerprint Indexing Technique based on Level-1 and Level-2 Features

Biometric feature is used for human identification and verification in access management of physical, virtual work space and many other real time applications. The current state-of-art biometric identification algorithm focuses on accuracy and hence works well in terms of response time on small scale database.In real life scenario biometric database are huge and without any intelligent scheme the response time should be high, but the existing algorithms requires an exhaustive search on the database which increases proportionally when the size of the database grows. A good indexing technique is essential to narrow down the search space. This work addresses the problem of biometric indexing in the context of fingerprint. Indexing is a technique to reduce the number of candidate identities to be considered by the identification algorithm. The fingerprint indexing methodology projected in this work is based on a combination of Level-1 and Level-2 features. The result obtained portraits the combination of level-1 and level-2 features capitulates better performance than with any one feature.