Peter Rot

Peter Rot is a researcher at the Faculty of Computer and Information Science, University of Ljubljana, specializing in Computer Vision and Biometrics. He is affiliated with the Computer Vision Laboratory (LRV) and has contributed to privacy-enhancing technologies in biometric systems.

• Education: Master of Computer Science and Informatics (University of Ljubljana, 2018) with thesis on "Deep Learning Methods for Biometric Recognition Based on Eye Information"

Research Focus: His work addresses soft-biometric privacy, deepfake localization, and ocular biometrics, combining deep learning and generative models to protect facial attributes while maintaining recognition accuracy. Notable projects include FaceGEN (ARRS J2-1734) and DeepBeauty (ARRS J2-2501).

Publications & Trends: Recent work explores privacy-preserving face analytics, interpretable biometric templates, and gender privacy through disentangled representations. Earlier studies focused on sclera segmentation and periocular recognition.

• Scientific Awards:
  • European Association for Biometrics Biometric Research Award 2024
  • EAB Best Presentation Award 2024
  • University Prešernova Award 2018
  • Sclera Segmentation Competition Winner 2018
  • Sclera Segmentation and Eye Recognition Competition Winner 2017

Projects: Currently leads the MIXBAI project (ARRS J2-50069) on explainable biometric AI (2023-2026). Past projects include FaceGEN (2019-2022) for face de-identification and DeepBeauty (2020-2023) for generative models in fashion/beauty industries.