While traditional fingerprint recognition algorithms have been proven useful to detect and compare “minutiae” to identify human subject, there is still research devoted to understand which number of features should be used for the identification. In this regard, Deep Learning algorithms can help in performing statiscal analysis over finger print datasets.
Therefore, the candidate is expected to review the state of the art of Deep Learning techniques for fingerprint recognition. In addition, she/he will develop experiments to evaluate and compare different models, with the goal of finding the most adequate model to perfom the statistical analysis over real datasets.
The thesis will be developed at the Information Engineering Department of the “Università Politecnica delle Marche” as part of the Memorandum of Understanding between the “Centro Interdipartimentale CARMELO” and the “Ministero dell’Interno, Dipartimento di Pubblica Sicurezza, Direzione Centrale Anticrimine della Polizia di Stato”
Involed tools and technologies: Keras, TensorFlow, Google Colab, Python, and similar.