U.S. Army Research Laboratory (ARL) scientists have developed a new face recognition technology that works well in nighttime and low-light conditions.
The technology which is capable of producing a visible face image from a thermal image of a person’s face captured in low-light or nighttime conditions, could lead to enhanced real-time biometrics and post-mission forensic analysis for covert nighttime operations.
The system which is being viewed as an extension of thermal cameras like Forward Looking Infrared (FLIR), was developed by ARL’s Drs. Benjamin S. Riggan, Nathaniel J. Short and Shuowen “Sean” Hu.
“This technology enables matching between thermal face images and existing biometric face databases/watch lists that only contain visible face imagery,” said Riggan. “The technology provides a way for humans to visually compare visible and thermal facial imagery through thermal-to-visible face synthesis.”
The ARL approach leverages advanced domain adaptation techniques based on deep neural networks.
The fundamental approach is composed of two key parts: a non-linear regression model that maps a given thermal image into a corresponding visible latent representation and an optimization problem that projects the latent projection back into the image space.
The optimization problem for synthesizing an image attempts to jointly preserve the shape of the entire face and appearance of the local fiducial details.
Using the synthesized thermal-to-visible imagery and existing visible gallery imagery, the researchers performed face verification experiments using a common open source deep neural network architecture for face recognition.
The architecture used is explicitly designed for visible-based face recognition. The most surprising result is that ARL’s approach achieved better verification performance than a generative adversarial network-based approach, which previously showed photo-realistic properties.
Image and content: Eric Proctor, William Parks and Benjamin S. Riggan/U.S. Army Research Laboratory