Usability Testing of Face Image Capture for US Ports of Entry

Abstract

The requirements necessary for taking a successful face picture are arguably the least constrained of any biometric. The camera must be operational, and the subject must be illuminated sufficiently & facing the camera. Yet, a significant portion of the faces taken at US ports of entry are unusable for the purposes of automatic face recognition. In this paper, we consider the usability components of the face image capture process that contribute to the relatively high ratio of unusable images collected by United States Visitor and Immigrant Status Indicator Technology (US-VISIT). In addition, we introduce a general evaluation methodology - including the use of a simple image overlay - to quantify various characteristics of face imagery. The experimental context mimicked the point-of-entry environment, but with specific usability enhancements. The collected data suggests that these usability enhancements may be used to improve face image capture with equipment that is capable of capturing faces with a near-zero failure-to-enroll (FTE) rate.