ICT4SS - ICT FOR SMART SOCIETIES
Deep learning based biometric authentication
keywords DEEP LEARNING, VIDEO ANALYSIS
Reference persons ENRICO MAGLI
Thesis type RESEARCH
Description Digitized information is increasing leading to an increase in the importance of security. State-of-the-art results are obtained for the classification tasks using deep learning.
In this thesis, the candidate will design a deep neural network which could authenticate different biometries like Face, Fingerprints and Retina etc. The aim will be to use the deep learning in conjunction with statistical models to enforce the authorized users to a specific probability distribution, and unauthorized users to another distribution far away from the former.
Required skills Candidate students should have a background in ICT or mathematics. Knowledge of neural networks (including TensorFlow environment and Python programming) is not a prerequisite, although it would help in the initial stage of the activity.
Deadline 11/10/2019 PROPONI LA TUA CANDIDATURA