Yeole, Shashank (2018) Fingerprint Recognition System Using Method of Sectoralization. MTech thesis.
PDF Restricted to Repository staff only 1571Kb |
Abstract
Fingerprint consists of connected ridges with furrows between the space of the ridges. These patterns are influenced by the genetic as well as the random physical stress and tension during fetal development making them distinct. These patterns tend to persist over the lifetime of the individual. It makes fingerprint one of the most reliable biometric traits. Various fingerprint matching algorithms adopts different approaches: skeleton matching, image correlation, phase matching and minutiae matching. In this research we propose a minutiae based matching approach which will use one of the singular points as a reference point for the minutiae alignment. The technique will compute different sectors based on the distance from the reference point which will reduce the matching time for non similar fingerprints. In comparison to the existing minutiae matching algorithm, our results show that the computational delay is reduced.
Item Type: | Thesis (MTech) |
---|---|
Uncontrolled Keywords: | biometrics; fingerprint; feature extraction; Minutiae; Feature vector; Sectoralization. |
Subjects: | Engineering and Technology > Computer and Information Science > Image Processing |
Divisions: | Engineering and Technology > Department of Computer Science Engineering |
ID Code: | 9634 |
Deposited By: | IR Staff BPCL |
Deposited On: | 27 Mar 2019 17:25 |
Last Modified: | 27 Mar 2019 17:26 |
Supervisor(s): | Bakshi, Sambit |
Repository Staff Only: item control page