A team of researchers has developed a new technique that uses thermal-imaging to peer through the cosmetics that could potentially confuse facial recognition algorithms.The scientists from the U.S. Army Research Laboratory in Maryland, say that biometric facial-recognition systems based on visible imaging can be severely inhibited by make-up.In a study published in in the journal Applied Optics, from The Optical Society (OSA), the team describe an identification method that uses so-called polarimetric-thermal imagery.”Our study has demonstrated polarimetric-thermal imaging can be substantially more robust to face paints, and to a degree cosmetics, for facial recognition than visible imaging,” said Nathaniel Short, the lead researcher, who is on contract with U.S. Army Research Laboratory as part of the Image Processing Branch, told Phys.org on the study.Identifying faces using visible-light imaging can be impact as reflected light from the key edges of the faces, and edges of the eyes, nose and mouth, can be changed by cosmetics.”Our experiments show how face paints and cosmetics degrade the performance of traditional facial-recognition methods and we provide a new approach to mitigating this effect using polarimetric-thermal imaging.”Beyond defeating the threat posed by cosmetics, the study also looks at the benefits of polarimetric-thermal imaging for night -time face recognition tasks.
Select Page















