Simple steps to improve quality of facial images taken at border entry points

Washington, November 26 : Researchers at the National Institute of Standards and Technology (NIST) say that officials at border entry points, such as airports and seaports, can acquire better quality facial images of travellers with the aid of the existing technology itself if they adopt certain simple steps.

Lead researcher Mary Theofanos has revealed that to find out how to obtain better facial images without having to deploy new technology, her team first visited and observed a Department of Homeland Security (DHS) border entry point at Dulles Airport in the Washington, D.C. area, where all travellers have their pictures taken and their fingerprints collected digitally as part of the US-VISIT program.

Having closely observed the facial-image capturing process, the researchers identified and shared with US-VISIT a number of steps to take for acquiring better images.

They recommended that operators should adjust camera settings to ensure the subject comes into sharp focus, and that a traditional-looking camera be used in facial-recognition systems so that individuals could clearly recognize the camera and look into it.

After the Dulles site visit, a study was also conducted to see whether the recommendations of the research team were actually workable.

The researchers took facial images of 300 participants while mimicking the real-world conditions of a border entry point, and, interestingly, all of the pictures clicked fully captured the participant's face.

All of the participants faced the camera, and the researchers found additional improvements by using a graphical overlay to the camera display in order to better position the camera.

Based on their observations, the researchers came to the conclusion that such steps can improve the performance of facial recognition systems in real-world settings using the existing technology.

A follow-up study is underway in which the researchers are incorporating the graphical overlay into the workflow of camera operators.

ANI