Human skin detection technology for improved security

Washington DC: Researchers have developed a novel 2D technology which uses the absorption characteristics of melanin, haemoglobin and water to better characterise human skin for improved security, search and rescue.

Colour-image based systems are excellent at locating people in aerial search and rescue operations but fall short when it comes to discerning between actual human skin and objects with similar hues.

A team from the US Air Force Institute of Technology (AFIT) have used feature spaces to key in on specific constituents of human tissue by using a skin index concerned with how water and melanin's presence in skin manifests at two different wavelengths in the near-infrared region.

These changes would cut the overall cost of hyperspectral-based search and rescue systems by a factor of seven.

"The features were designed based on an understanding of the physics behind skin's spectral shape but in such a way that the features separated skin and non-skin pixels in order to make the pattern recognition portion of the problem more effective," explained Michael J. Mendenhall, assistant professor at Air Force Institute of Technology.

"After a lot of investigation, we arrived at a simple observation that skin is more red than green due to the melanin in darker skin and oxygenated haemoglobin in lighter skin, whereas many of the false alarm sources were more green than red," Mendenhall noted.

Many current image recognition programmes engineer to search for a wide variety of objects -- exoplanets, oil wells or human skin, to name a few -- by looking for specific "fingerprints" in the electromagnetic spectrum.

Mendenhall and his colleagues use their skin detection and false alarm suppression feature space to design an application-specific optical system using three framing cameras.

Because their skin detection solution can be implemented with less expensive technology capable of live video frame rates, its total price tag would be around $100,000.

The skin detection approach is described in the journal Applied Optics.