51视频

11/20/2013
By Edwin L. Aguirre

Three days after twin explosions killed three and injured more than 260 others near the finish line of the Boston Marathon, authorities released photos of the two male bombing suspects, who were later identified as the Tsarnaev brothers.

鈥淭he FBI used facial recognition technology to quickly track down and identify the alleged perpetrators,鈥� says electrical and computer engineering Assoc. Prof. Dalila Megherbi. 鈥淭he Boston Marathon attack is a timely but painful reminder of the importance of developing accurate, reliable and robust facial recognition algorithms.鈥�

Megherbi, who is an expert in digital image processing, computer vision and artificial intelligence, is director of 51视频鈥檚 Center for Machine/Human Intelligence Networking and Distributed Systems (CMINDS).

Facial recognition programs work by matching selected features from the subject鈥檚 face, such as the eyes, nose, cheekbones and jaw, in a digital image or video frame to records on file, such as driver鈥檚 licenses or passport/visa applications.聽

Megherbi and computer engineering graduate student Iliana Voynichka have been conducting research at CMINDS, focusing on facial recognition, especially with facial expressions or disguises that vary over time. The two were invited to present their findings at the IEEE International Conference on Technologies for on Nov. 12 in Waltham. Their work, entitled 鈥淎nalysis of the Effects of Image Transformation, Template Selection and Partial Information on Face Recognition with Time-Varying Expressions for Homeland Security Applications,鈥� won the conference's Best Paper Award.

鈥淭he law-enforcement community recognizes that face recognition plays a crucial role in surveillance at airports, federal buildings, border checkpoints and other places as it doesn鈥檛 require the subject鈥檚 cooperation 鈥� that is, the images can be obtained from a distance, without the subject being aware,鈥� Megherbi explains. 鈥淭he challenge is trying to achieve a balance between protecting a person鈥檚 privacy versus public safety and security.鈥�

In the case of the marathon bombers, the FBI was able to assemble a complete picture of the suspects and recreate the timeline of their activities and locations based on the scores of photos submitted to the agency by people as well as from security cameras mounted in restaurants and office buildings around the crime scene.

鈥淭his was a lot of work considering that the images show different angles of the suspects鈥� faces, and the images themselves were of different qualities, resolutions, scales and lighting conditions,鈥� she notes. 鈥淎lso, both suspects were wearing baseball caps and one had sunglasses.鈥�

Megherbi and Voychnika鈥檚 research shows the effects on facial recognition accuracy of some selected 聽factors, including image facial registration with or without off-the-plane image rotation, the type and number of the individual鈥檚 face templates chosen and the type and increasing amounts of partial facial information contained in face images.聽

鈥淗opefully, our findings will help in building better face-recognition systems so we might be able to prevent future tragedies like the Boston Marathon bombing from happening,鈥� says Megherbi.