Utilize este identificador para referenciar este registo:
https://hdl.handle.net/10316/115039
Título: | MorDeephy: Face Morphing Detection via Fused Classification | Autor: | Medvedev, Iurii Shadmand, Farhad Gonçalves, Nuno |
Palavras-chave: | Face Morphing Detection; Face Recognition; Deep Learning; Convolutional Neural Networks; Classification | Data: | 2023 | Editora: | Science and Technology Publications, Lda | Projeto: | Portuguese Mint and Official Printing Office (INCM) and the Institute of Systems and Robotics-the University of Coimbra - project Facing. UIDB/00048/2020 |
Título da revista, periódico, livro ou evento: | International Conference on Pattern Recognition Applications and Methods | Resumo: | Face morphing attack detection (MAD) is one of the most challenging tasks in the field of face recognition nowadays. In this work, we introduce a novel deep learning strategy for a single image face morphing detection, which implies the discrimination of morphed face images along with a sophisticated face recognition task in a complex classification scheme. It is directed onto learning the deep facial features, which carry information about the authenticity of these features. Our work also introduces several additional contributions: the public and easy-to-use face morphing detection benchmark and the results of our wild datasets filtering strategy. Our method, which we call MorDeephy, achieved the state of the art performance and demonstrated a prominent ability for generalizing the task of morphing detection to unseen scenarios. | URI: | https://hdl.handle.net/10316/115039 | DOI: | 10.5220/0011606100003411 | Direitos: | openAccess |
Aparece nas coleções: | I&D ISR - Artigos em Revistas Internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
MorDeephy Face Morphing Detection via Fused Classification_arXiv.pdf | 4.45 MB | Adobe PDF | Ver/Abrir |
Visualizações de página
25
Visto em 17/jul/2024
Downloads
4
Visto em 17/jul/2024
Google ScholarTM
Verificar
Altmetric
Altmetric
Este registo está protegido por Licença Creative Commons