Below is the uncorrected machine-read text of this chapter, intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text of each book. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.
239Â Â Accuracy of Facial Recognition With the application of facial-recognition systems in aviation, it is important that all stake- holders are aware of how accurate these systems are. Inaccurate capturing equipment or facial-recognition technology causing a false positive match must not result in allowing a passenger to gain illegal passage at a border checkpoint or to illegally enter a plane. The algorithm should not be so strict that almost every person that approaches a touchpoint is rejected, nor should the time to render the decision be too long. There needs to be a balance between security and facilitation. The matching algorithm analyzes the features stored in the biometric template on enroll- ment with the features derived from the image made of the live person on verification to pro- duce a similarity score. If the score reaches a certain threshold, the algorithm decides that it is a match. A biometric system will never result in a 100% match. This is because it depends on the quality and amount of useful information that can be extracted from the image. The quality of useful information depends on varying conditions between enrollment and verification but also on the difference in appearance of the person that needs to be identified (e.g., aging, glasses, face mask). Accuracy relates to the number of times that the system gives the correct response. For the response, two variables are most important in operation: the false acceptance rate (FAR) and the false rejection rate (FRR). The FAR is the relative number of passengers that can pass through to the system who should not be allowed to do so. The FRR is the relative amount of passengers that are rejected by the system when they had the right to pass. An increase in the size of the database will lead to a lower accuracy, with higher false acceptances because there will be more similar biometric templates. Raising the threshold too high will lead to a low FAR but may also lead to longer processing times. Which rates are acceptable are to be determined by the authorities and other stakeholders. The performance of different face-recognition algorithms from different vendors is reported on a frequent basis by NIST. NIST has been testing the performance of face-match algorithms since 2017 by using a standard measuring method against large image databases. Although the accuracy depends on many other factors of the system as well, the performance of the facial- recognition algorithm is the basis of a reliable face-recognition system. In the facial-recognition algorithm, the similarity threshold can be adjusted, and this will affect the FRR and FAR. After installation of the biometric verification touchpoints at the location, the system needs to be tested and commissioned. When the system is accepted and operational, it can be load tested by having live people enrolled and passing through the bio- metric touchpoints. Fine tuning may include, for example, adjusting the uniform illumination A P P E N D I X O
240 Airport Biometrics: A Primer level of the touchpoint or protecting the camera view from backlight. After some time, the system can be checked for the FRR. In the passenger facilitation process, it is also possible that the face that is presented for verification does not exist in the database. A passenger that did not enroll in the program will not have a biometric template in the database. The system will give a rejection, but it is not false. After a series of attempts, the system should raise an alarm, and manual intervention will be needed.
Abbreviations and acronyms used without definitions in TRB publications: A4A Airlines for America AAAE American Association of Airport Executives AASHO American Association of State Highway Officials AASHTO American Association of State Highway and Transportation Officials ACIâNA Airports Council InternationalâNorth America ACRP Airport Cooperative Research Program ADA Americans with Disabilities Act APTA American Public Transportation Association ASCE American Society of Civil Engineers ASME American Society of Mechanical Engineers ASTM American Society for Testing and Materials ATA American Trucking Associations CTAA Community Transportation Association of America CTBSSP Commercial Truck and Bus Safety Synthesis Program DHS Department of Homeland Security DOE Department of Energy EPA Environmental Protection Agency FAA Federal Aviation Administration FAST Fixing Americaâs Surface Transportation Act (2015) FHWA Federal Highway Administration FMCSA Federal Motor Carrier Safety Administration FRA Federal Railroad Administration FTA Federal Transit Administration GHSA Governors Highway Safety Association HMCRP Hazardous Materials Cooperative Research Program IEEE Institute of Electrical and Electronics Engineers ISTEA Intermodal Surface Transportation Efficiency Act of 1991 ITE Institute of Transportation Engineers MAP-21 Moving Ahead for Progress in the 21st Century Act (2012) NASA National Aeronautics and Space Administration NASAO National Association of State Aviation Officials NCFRP National Cooperative Freight Research Program NCHRP National Cooperative Highway Research Program NHTSA National Highway Traffic Safety Administration NTSB National Transportation Safety Board PHMSA Pipeline and Hazardous Materials Safety Administration RITA Research and Innovative Technology Administration SAE Society of Automotive Engineers SAFETEA-LU Safe, Accountable, Flexible, Efficient Transportation Equity Act: A Legacy for Users (2005) TCRP Transit Cooperative Research Program TDC Transit Development Corporation TEA-21 Transportation Equity Act for the 21st Century (1998) TRB Transportation Research Board TSA Transportation Security Administration U.S. DOT United States Department of Transportation
Transportation Research Board 500 Fifth Street, NW Washington, DC 20001 ADDRESS SERVICE REQUESTED ISBN 978-0-309-67430-0 9 7 8 0 3 0 9 6 7 4 3 0 0 9 0 0 0 0
