A Quantitative Evaluation Framework of Video De-Identification Methods
Contributo in Atti di convegno
Data di Pubblicazione:
2021
Citazione:
A Quantitative Evaluation Framework of Video De-Identification Methods / S. Bursic, A. D'Amelio, M. Granato, G. Grossi, R. Lanzarotti (INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION). - In: 2020 25th International Conference on Pattern Recognition (ICPR)[s.l] : IEEE, 2021. - ISBN 978-1-7281-8808-9. - pp. 6089-6095 (( Intervento presentato al 25. convegno International Conference on Pattern Recognition (ICPR) tenutosi a on line nel 2021 [10.1109/ICPR48806.2021.9412186].
Abstract:
We live in an era of privacy concerns, motivating a large research effort in face de-identification. As in other fields, we are observing a general movement from hand-crafted to deep learning methods, mainly involving generative models. Although these methods produce more natural de-identified images or videos, we claim that the mere evaluation of the de-identification is not sufficient, especially when it comes to processing the images/videos further. In this note, we take into account the issue of preserving privacy, facial expressions, and photo-reality simultaneously, proposing a general testing framework. The quantitative evaluation is applied to four open-source tools, producing a baseline for future de-identification methods.
Tipologia IRIS:
03 - Contributo in volume
Elenco autori:
S. Bursic, A. D'Amelio, M. Granato, G. Grossi, R. Lanzarotti
Link alla scheda completa:
Titolo del libro:
2020 25th International Conference on Pattern Recognition (ICPR)