Customs and Border Protection launches passport facial recognition airport pilot
The Department of Homeland Security announced that Customs and Border Protection has initiated its “1:1 Facial Recognition Air Entry Pilot” program to allow CBP officers (CBPOs) at airports to use facial recognition technology to help verify the identities of US electronic passport holders, according to a report by Homeland Security Today.
DHS’s Privacy Office is legally required to provide continued guidance on all privacy issues relating to key technologies in which the private data of citizens is collected for training and testing purposes, such as in the case of the Facial Recognition Air Entry Pilot program.
As a result, the Privacy Impact Statement (PIA) was required to analyze the privacy impact of the 1:1 Facial Recognition Air Entry Pilot and the collection of facial image data to ensure that it adheres to the DHS Privacy Office’s Fair Information Practice Principles.
The Facial Recognition Air Entry Pilot program’s goals “are to determine the viability of facial recognition as a technology to assist CBP Officers in identifying possible imposters using US e-passports to enter the United States and determine if facial recognition technology can be incorporated into current CBP entry processing with acceptable impacts to processing time and the traveling public while effectively providing CBPOs with a tool to counter imposters using valid US travel documents.”
CBP is running the pilot program at a select number of airports of entry “after having successfully completed testing in a laboratory environment.”
The pilot’s results show that the system successfully performed matches when tested against passports and live captured images, as well as detected imposters when comparing a fraudulent passport against a live captured image.
During the pilot program, CBP takes a photo of the US passport holder, applies facial recognition software algorithms to compare the captured image against the image displayed on the e-passport, and then uses the results to help verify the person’s identity.
The PIA said that two errors can happen during the entry process. The first is called a False Non-Match Rate (FNMR), which occurs if a CBPOs agent does not correctly match the e-Passport photo to the document holder.
The second is a False Acceptance Rate (FAR), which occurs when a CBPOs agent “incorrectly matches an e-passport photo with an imposter physically in front of him or her.” A FAR error is the more severe of the two errors as it could allow an imposter to enter the U.S.
After the e-passport chip is scanned and the photo is taken, the software generates a match confidence score based on algorithms designed to detect possible imposters.
The 1:1 Facial Recognition Air Entry Pilot intends on maximizing the number of imposters caught (True Non-Match Rate) while minimizing traveler inconvenience and CBPOs impacts.
The pilot will take approximately 19 months to complete, including testing and analysis, however, CBPOs agents “will only use the technology to capture photographs from US e-passport holders for 60 days,” said PIA.
US citizens with US e-passports arriving at airports of entry where CBP is testing the facial recognition technology may be randomly chosen by CBPOs agents to take part in the mandatory test.