Infrared imaging identifies skin to support face recognition
A research team at the Bonn-Rhein-Sieg University of Applied Sciences has developed a skin detection process based on infrared imaging to support biometric systems in identifying faces.
The solution, which uses multispectral and infrared imaging, is designed to overcome the risk of a biometric system being fooled by a person wearing a mask.
A reliable security system must be able to differentiate between human skin and other materials while concurrently checking biometric characteristics.
The scientists based their method on imaging at wavelengths between 900nm and 1,500nm. At approximately 1,450nm, the skin displays characteristic absorption characteristics, independent of skin type. Also, above 900nm, skin pigments have no influence on albedo, or reflection coefficient, and therefore absorption of the light by water in the skin also gives a characteristic output.
The investigation was implemented with an active camera system in which an infrared camera – the Goldeye G-032 SWIR model from Allied Vision – is mounted in the middle of a ring of LEDs. Three rows of LEDs transmit light in different wavelengths within the defined range onto the face to be analysed. The camera records the reflected short-wave infrared light. The data is made available on a PC using Allied Vision’s software development kit, Vimba.
When facial recognition systems are equipped with these camera systems, they only authenticate users if facial characteristics are correct and recognised as skin.
Scientists at Bonn-Rhein-Sieg University of Applied Sciences are using similar skin detection technology to provide safeguards for humans working with machines. The system can recognise when a human’s hand crosses into a danger zone, for instance, and halt the machinery.