The U.S. Department of Homeland Security (DHS) Science and Technology Directorate (S&T) announced the launch of a new dataset of synthetic carry-on baggage images to help secure and speed up screening at airports.
The new initiative gives screeners access to high-quality data about the carry-on baggage as part of a move to make baggage screening faster and more accurate, officials said. The initiative supports President Donald Trump’s executive orders to secure public safety and improve trade and travel, while helping innovators speed the creation of next-generation screening technology, the agency said.
“Detection algorithms are key to reducing false alarms that cause hands-on bag inspections and longer checkpoint wait times,” Pedro Allende, DHS Under Secretary for Science and Technology, said. “Enabling rapid algorithm development from the best innovators not only will increase detection accuracy at the checkpoint but also improve the traveler experience.”
Currently, only a limited number of bag images are available to train carry-on baggage algorithms and developers have to undergo vetting in order to view them, officials said. This can deter some from developing new screening technologies.
In response, Cignal LLC, of Reedsville, Pa., has developed synthetic images for S&T’s Screening at Speed Program, which includes 250 computed tomography (CT) X-ray images that mirror scans produced by the Transportation Security Administration’s latest detection systems. Officials said future releases may feature larger, more complex bag sets and synthetic millimeter wave images for use in training passenger screening system.
S&T funded the technology through the Silicon Valley Innovation Program, linking innovators with Homeland Security enterprise challenges.