Bachelor/Master Thesis: Machine learning / Computer vision for Biometrics applications

Moderator: Aktive Fachschaft

Forumsregeln
Auch ohne Registrierung können Beiträge in diesem Unterforum geschrieben werden.
naser.damer
Neuling
Neuling
Beiträge: 8
Registriert: 9. Apr 2013 16:03

Bachelor/Master Thesis: Machine learning / Computer vision for Biometrics applications

Beitrag von naser.damer »

Bachelor/Master Thesis Proposal

Title: Machine learning / Computer vision for Biometrics applications

Contact@Fraunhofer IGD: Dr. Naser Damer (naser.damer@igd.fraunhofer.de). Competence Center Smart Living and Biometric Technologies, Fraunhofer IGD

Motivation:
Biometrics is a rapidly growing technology that aims to identify or verify people identities based on their physical or behavioral properties. Different aspects of biometric technology are an active research fields. Enhancing the accuracy of biometric comparisons, securing the biometric templates, managing fast searches in biometric databases, and detecting different attacks on biometric systems, are all essential advancements to enable a wider and more secure deployment of the technology. Most biometric systems are based on image analyses. Therefore, exciting challenges in the computer vision domain is inherited by biometric systems. Such challenges are related to miniature deep learning networks, explainable decisions, and domain adaption.

Our team is offering a number of open thesis positions to tackle these challenges. Interested students from Informatics, electrical engineering, mathematics, and physics, are encouraged to apply. The exact details of the thesis topic can be built on the available topics, and the competences and interests of the student.

The thesis:
The goal of the thesis is to perform state-of-the-art research in computer vision and machine learning for biometrics applications. The exact topic description can be tailored based on the research direction and student interests. The topics can target one of the following domains: Embedded and mobile biometrics, efficient machine learning, detecting and mitigating attacks on biometric systems, enhancing the explainability of biometric solutions, and enhancing the generalizability of computer vision solutions.

Required skills: Interest in machine learning and computer vision, good programming skills.

Study programs: Informatics, electrical engineering, mathematics, physics.

Contact: Dr. Naser Damer (naser.damer@igd.fraunhofer.de)

Please start your email title with: [THESIS APPLICANT]

Key literature:
[1] Naser Damer, Fadi Boutros, Florian Kirchbuchner, Arjan Kuijper: D-ID-Net: Two-Stage Domain and Identity Learning for Identity-Preserving Image Generation From Semantic Segmentation. ICCV Workshops 2019: 3677-3682
[2] Fadi Boutros, Naser Damer, Florian Kirchbuchner, Arjan Kuijper: Eye-MMS: Miniature Multi-Scale Segmentation Network of Key Eye-Regions in Embedded Applications. ICCV Workshops 2019: 3665-3670
[3] Philipp Terhörst, Jan Niklas Kolf, Naser Damer, Florian Kirchbuchner, Arjan Kuijper: SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness. CVPR 2020: 5650-5659
[4] Naser Damer, Alexandra Mosegui Saladie, Andreas Braun, Arjan Kuijper: MorGAN: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Generative Adversarial Network. BTAS 2018: 1-10
[5] Naser Damer, Kristiyan Dimitrov: Practical View on Face Presentation Attack Detection. BMVC 2016

Zurück zu „Abschlussarbeiten“