Face in video evaluation (FIVE) face recognition of non-cooperative subjects

Abstract

The report is organized with an executive summary, a high-level background, and a technical summary preceeding the main body of the report which gives more detailed information on participation, test design, performance metrics, datasets, and the results. � Overview: This report documents the Face in Video Evaluation (FIVE), an independent, public test of face recognition of non-cooperating subjects who are recorded passively and are mostly oblivious to the presence of cameras. The report enumerates accuracy and speed of face recognition algorithms applied to the identification of persons appearing in video sequences drawn from six different video datasets mostly sequestered at NIST. These datasets represent video surveil lance, chokepoint, and social media applications of the technology. In six cases, videos from fixed cameras are searched against portrait-style photographs of up to 48 000 enrolled identities. In one case, videos are searched against faces enrolled from other videos. Additionally, the effect of supplementing enrollment with non-frontal images is examined.� Participation: FIVE was open to any organization worldwide, at no charge. The research arms of sixteen major com mercial suppliers of face recognition technologies submitted thirty six algorithms, allowing FIVE to document a robust comparative evaluation. The algorithms were submitted to NIST in December 2015 so this report does not capture re search and development gains since then. The algorithms are research prototypes, evaluated as black boxes without developer training or tuning. They implement a NIST-specified interface and so may not be immediately commercially available. They run without graphical processing units (GPU).� Difficulty: Face recognition is much more difficult in non-cooperative video than with traditional portrait-style photos.The initial face detection task is non-trivial because a scene may contain no faces or may contain many, and these can appear over a range of resolutions (scales), orientations (poses), and illumination conditions. Second, subjects move, so their faces must be tracked through time and this is harder when motion blur occurs or when a face is occluded by closer persons or objects. Third, resolution in video is compromised by optical tradeoffs (magnification, field of view, depth of field, cost) and then by compression used to satisfy data rate or storage limitations. Finally, other adverse aspects of image quality and face presentation degrade recognition scores so that scores from unrelated individuals can be similarly high, making discrimination between known and unknown individuals error prone. This leads to the possibility that a member of the public can be falsely matched to someone on a watchlist; the occurence of such hazards is mitigated by elevating a recognition threshold.� Key conclusions: This study was conducted to support new and existing applications of face recognition, particularly to assess viability and technology readiness. These range from surveillance, to expedited single-facto...

Ongoing face recognition vendor test (FRVT) part 2:

“…ten years for a passport). While the distribution of dates for such images of a person might be assumed uniform, a number of factors might undermine this assumption 7 . In criminal applications, the number of images would depend on the number of arrests.…”

“…In any case, the 2010 NIST evaluation of face recognition showed that considerable accuracy benefits accrue with reten- 7 For example, a person might skip applying for a passport for one cycle, letting it expire. In addition, a person might submit identical images (from the same photography session) to consecutive passport applications at five year intervals.…”

Ongoing Face Recognition Vendor Test (FRVT) part 6B :

“…acting to evade face detection and recognition. Those applications are often characterized by image properties (low resolution, video compression, uncontrolled head orientation) that are known [5] to degrade recognition accuracy. 2020/11/30 08:35:54 FNMR(T) "False non-match rate" FMR(T) "False match rate"…”

Technology Gap Navigator: Emerging Design of Biometric-Enabled Risk Assessment Machines

“…Technology Gap (TG) navigation is a mechanism for 1) the analysis of the difference between required and available technologies, and 2) generating certain conditions for bridging this TG, given a design scenario or a task. For example, a resent study [GNQ17] addresses the state-of-the-art in the identification of non-cooperative individuals, such as surveillance in mass-transit systems. Another example of a TG [Nu14] involves the operational performance of biometric-based recognition in border control systems, which is significantly lower than a "theoretical" performance.…”