Multimodal soft biometrie verification by hand shape and handwriting motion in the air

Abstract

In the last decade, soft biometric traits have emerged as more convenient and non-intrusive alternatives for person authentication task. However a soft biometric trait cannot be a main feature for person authentication because it lacks distinctiveness compared with fingerprint, palm vein pattern and so on. Therefore this study proposes a person verification method integrating handwriting motion in the air and a shape of a hand, which can be successively measured by a device (RGB and depth camera). As the result of person verification experiment for 10 subjects, we obtained a good verification performance that FAR is 2% when FRR is 0%.