Authors:
D. Palma
Date:
2014
Publisher:
University of Udine
Cite:
D. Palma, "Design and development of a robust, non-invasive, and touch-less palmprint-based biometric recognition system," Bachelor's thesis, University of Udine, Italy, 2014.
Bibtex:
@misc{Palma2014BSc,
title = {Design and development of a robust, non-invasive, and touch-less palmprint-based biometric recognition system},
author = {Palma, David},
note = {Bachelor's Thesis, University of Udine},
year = {2014}
}Abstract:
Biometric systems are suitable to be used in various fields, such as high security, forensic and commercial applications. Palmprint recognition, a relatively novel but promising biometric technology, has recently received considerable interest, mostly for its importance in forensics and for several potential civil and security applications. This thesis presents a robust, non-invasive, and touch-less palmprint-based biometric recognition system, which is able to automatically identifying a person from a digital image of the hand acquired by a low-resolution CMOS camera. After a preprocessing step, which is required to extract the region of interest, the feature extraction process is applied. The latter involves a non-linear ordinary differential equation (ODE) whose output gives the feature vector to be compared, while the matching process makes use of the Pearson product-moment correlation coefficient to measure the similarity between two feature vectors. Moreover, in order to allow implementation on mobile (or embedded) devices, each step has been specifically designed to limit memory requirement and computational complexity.