Facial Anti-Spoofing Using “Clue Maps”
Liang Yu Gong, Xue Jun Li, Peter Han Joo Chong · 2024
Read Facial Anti-Spoofing Using “Clue Maps” by Liang Yu Gong, Xue Jun Li, Peter Han Joo Chong (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11644954.txt.
Description
Liang Yu Gong, Xue Jun Li, and Peter Han Joo Chong build a system that spots fake faces shown to recognition cameras. Printouts, replayed videos, and masks can fool face checks and open bank accounts to fraud. Their 2024 method trains an encoder-decoder network to draw what they call clue maps. These maps distill signs of fakery into one shared picture form, which a helper classifier then reads.
Training mixes three loss types to sharpen both the maps and the calls. On three public test sets the method beat prior models, with error near one percent inside one set. Across unlike sets it set a new best mark as well. The authors stress low cost, since only plain color images are needed.
Catalog record
| CREATOR | Liang Yu Gong, Xue Jun Li, Peter Han Joo Chong |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |