Skip to content

Deep Models and Shortwave Infrared Information to Detect Face Presentation Attacks

Description

We explored the use of short wave infrared (SWIR) imaging for Face Presentation Attack Detection (PAD). Face PAD is performed using recent models based on Convolutional Neural Networks using only carefully selected SWIR image differences as input.

Publications

Heusch, G. and George, A. and Geissbuhler, D. and Mostaani, Z. and Marcel, S. (2020). Deep Models and Shortwave Infrared Information to Detect Face Presentation Attacks. IEEE Transactions on Biometrics, Behavior, and Identity Science.

Links

Advantages

The proposed approach has shown superior performance over similar models acting on either color images or on a combination of different modalities (visible, NIR, thermal and depth) and is able to almost perfectly detect all impersonation attacks while ensuring low bona classification errors.

Applications

  • Face Recognition
  • Security

Technology Readiness Level

TRL 5

FPAD-SWIR

MC-PixBiS architecture with pixel-wise supervision. SSWIR images differences are stacked before being passed to a series of dense blocks.

Contact us for more information

  • Interested in using our technologies?
  • Interested to know more about the licensing possibilities and conditions?

Contact us