CMINDS Research in Homeland Security Relates to Boston Bombing

UMass Lowell Image
Facial Recognition


The Boston Marathon attack is a timely and painful reminder of the importance of developing accurate, reliable facial recognition algorithms. Some recent research at the CMINDS has been focusing on facial recognition, especially with time-varying facial expressions and/or disguises, which are crucial in many homeland security applications.  

In particular, in this research work Prof. Megherbi and her student, Iliana Voychnika, show the effects on facial recognition accuracy of some selected factors including image facial registration with or without off-the-plane image rotation, the type and number of individual’s face template(s) selection, and the type and increasing amounts of partial facial information contained in face images. Professor Megherbi and her student have been invited to present these findings and related experimental results at the IEEE Homeland Security Conference in Fall 2013.