ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 FaceBERT: Face De-Identification Using VQGAN and BERT
Cited 1 time in scopus Download 4 time Share share facebook twitter linkedin kakaostory
저자
임동혁, 서용석
발행일
202210
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2022, pp.2013-2015
DOI
https://dx.doi.org/10.1109/ICTC55196.2022.9952883
협약과제
22IH2400, 교육콘텐츠에 대한 인공지능 기반 저작권 침해 의심요소 검출 및 대체 재료 콘텐츠 추천기술 개발, 서용석
초록
This paper presents FaceBERT, a face de-identification technique based on image generation to solve the infringement of portrait rights. Using the VQGAN model, it learns a quantized codebook that expresses an image in block units, encodes the image using the codebook, and then trains the BERT model. As a result of an experiment using FFHQ and CelebA-HQ, it was confirmed that the face images generated using FaceBERT were natural de-identified face images and different from the originals.
KSP 제안 키워드
Face Image, Identification techniques, Image generation, face de-identification