A5007881212- Face recognition and analysis
- Biometric Identification and Security
- Advanced Steganography and Watermarking Techniques
- Facial Nerve Paralysis Treatment and Research
- Digital Media Forensic Detection
- Advanced Vision and Imaging
- Color Science and Applications
- Internet Traffic Analysis and Secure E-voting
- Advanced Data Compression Techniques
- QR Code Applications and Technologies
- Face and Expression Recognition
- User Authentication and Security Systems
University of Coimbra
2021-2025
Institute for Systems Engineering and Computers
2021-2025
Face morphing attack detection (MAD) is one of the most challenging tasks in field face recognition nowadays.In this work, we introduce a novel deep learning strategy for single image detection, which implies discrimination morphed images along with sophisticated task complex classification scheme.It directed onto facial features, carry information about authenticity these features.Our work also introduces several additional contributions: public and easy-to-use benchmark results our wild...
Various modern security systems follow a tendency to simplify the usage of existing biometric recognition solutions and embed them into ubiquitous portable devices. In this work, we continue investigation development our method for securing identification documents. The original facial template, which is extracted from trusted frontal face image, stored on document in secured personalized machine-readable code. Such protected photo manipulation may be validated with an offline mobile...
Identity Documents (IDs) containing a facial portrait constitute prominent form of personal identification. Photograph substitution in official documents (a genuine photo replaced by non-genuine photo) or originally fraudulent with an arbitrary photograph are well known attacks, but unfortunately still efficient ways misleading the national authorities in-person identification processes. Therefore, order to confirm that identity document holds validated photo, novel face image steganography...
Face recognition has achieved outstanding performance in the last decade with development of deep learning techniques. Nowadays, challenges face are related to specific scenarios, for instance, under diverse image quality, robustness aging and edge cases person age (children elders), distinguishing identities. In this set problems, recognizing children's faces is one most sensitive important. One reasons problem existing bias towards adults datasets. work, we present a benchmark dataset...
Face morphing attack detection (MAD) is one of the most challenging tasks in field face recognition nowadays. In this work, we introduce a novel deep learning strategy for single image detection, which implies discrimination morphed images along with sophisticated task complex classification scheme. It directed onto facial features, carry information about authenticity these features. Our work also introduces several additional contributions: public and easy-to-use benchmark results our wild...