De-Duplication of Person's Identity Using Multi-Modal Biometrics

N, Pattabhi Ramaiah (2015) De-Duplication of Person's Identity Using Multi-Modal Biometrics. PhD thesis, Indian Institute of Technology Hyderabad.

CS10P005.pdf - Submitted Version

Download (8MB) | Preview


The objective of this work is to explore approaches to create unique identities by the de-duplication process using multi-modal biometrics. Various government sectors in the world provide different services and welfare schemes for the beneffit of the people in the society using an identity number. A unique identity (UID) number assigned for every person would obviate the need for a person to produce multiple documentary proofs of his/her identity for availing any government/private services. In the process of creating unique identity of a person, there is a possibility of duplicate identities as the same person might want to get multiple identities in order to get extra beneffits from the Government. These duplicate identities can be eliminated by the de-duplication process using multi-modal biometrics, namely, iris, ngerprint, face and signature. De-duplication is the process of removing instances of multiple enrollments of the same person using the person's biometric data. As the number of people enrolledinto the biometric system runs into billions, the time complexity increases in the de duplication process. In this thesis, three different case studies are presented to address the performance issues of de-duplication process in order to create unique identity of a person.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Item Type: Thesis (PhD)
Uncontrolled Keywords: multi-modal biometrics; fingerprints; iris; iris fibers; face; signature; de-duplication; de-noising; support vector machines; principle component analysis; online dictionary learning; slap fingerprint segmentation; iris classification; kernel transfor-mation learning; cross-sensor fingerprint recognition, TD331
Subjects: Computer science > Special computer methods
Computer science > Big Data Analytics
Divisions: Department of Computer Science & Engineering
Depositing User: Library Staff
Date Deposited: 07 May 2015 04:08
Last Modified: 14 May 2019 11:22
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 1494 Statistics for this ePrint Item