Air Force develops prototype for skin-ID sensor
- By Mark Pomerleau
- Feb 03, 2016
Researchers with the Air Force have developed an advanced sensing system that could aid in recovering injured soldiers by identifying their skin.
A prototype developed by the Sensors Exploitation Research Group at the Air Force institute of Technology differentiates human skin from other materials. Typical color-image based systems have high false detection rates, though the prototype uses a skin detection and color estimation approach that is more accurate and resourceful with requiring only a small number of spectral channels, as opposed to larger hyperspectral cameras, an Air Force release said.
“Our approach concentrates on the melanin and water in skin. It can detect the skin while providing a means to determine how much melanin it contains. Since melanin is the primary element contributing to skin's color, it's a valuable piece of information to extract," said Michael Mendenhall, an assistant professor at the Air Force Institute of Technology and leader of the Sensors Exploitation Research Group. “I can use our camera system to filter out skin types based on the details of the person of interest. We can show only fair skinned people, only dark skinned people, or anything in between. This is particularly useful in speeding up the search process and improving an analyst's ability to locate persons of interest.”
The military is constantly trying to improve sensing suites for greater accuracy in identifying targets and assets, as seen with a recent solicitation issued by the Air Force for “alternatives for materiel solutions to detect mobile targets and targets obscured by natural or man-made means from medium and high altitudes.”
The Sensors Exploration Research Group’s system can assess skin color in real-time, combining necessary information from the visible and near-infrared light spectrum to enable identification between human skin and other materials such as grass, trees or buildings, simultaneously filtering out skin colors that are not of interest, the release said.
Going forward, the research team would like to account for hair in skin for even greater accuracy. In terms of current improvements, the team wants to incorporate mirror-like reflections of skin into algorithms.
Mark Pomerleau is a former editorial fellow with GCN and Defense Systems.