BioLive
Abstract
Individuals can be recognized by their biological and behavioral characteristics such as face, voice and fingerprint. Biometric recognition systems allow the automation of the recognition process, by means of signal processing and machine learning methods. The project is inserted in this context and aims at exploring open-set authentication techniques for mobile devices. BioLive is a collaboration between Unicamp and Motorola Mobility LLC.
Publications
Cross-dataset emotion recognition from facial expressions through convolutional neural networks
Journal of Visual Communitation and Image Representation - 2021
Detecting face presentation attacks in mobile devices with a patch-based CNN and a sensor-aware loss function
PLOS ONE - 2020
Two-tiered face verification with low-memory footprint for mobile devices
IET Biometrics - 2020
Two-tiered facial verification for mobile devices
Workshop of Theses and Dissertations, 31st Conference on Graphics, Patterns and Images (WTD/SIBGRAPI)
A Competition on Generalized Software-based Face Presentation Attack Detection in Mobile Scenarios
International Joint Conference on Biometrics (IJCB 2017)
Talks
Two-tiered facial verification for mobile devices
16th International Summer School of Biometrics