January 14, 2015 -
The National Science Foundation is funding the research and development of an automatic attendance check system that uses smartphone cameras.
Detailed in the grant award outline, the I-Corps team’s “Automated Attendance Check by Using Smartphone Cameras” method proposes an efficient and accurate way to check attendance by taking videos of student faces in classrooms using smartphone cameras.
The team, led by Rathindra DasGupta, proposes a new system based on a unified framework of visual face detection, tracking and recognition algorithms, which is capable of recognizing multiple faces in the video simultaneously.
Instructors must first install the app on their smartphone, using the device’s camera to take a short-period video of student faces on the first day of class.
The application will automatically build a face dataset for the course and the instructor only needs to identify them for the initial class. From that point on, instructors simply take videos of each class and the application will automatically check the attendance.
The smartphone app will perform multi-object tracking to associate detected faces into face tracklets.
The face instances in each face tracklet are then grouped into a small number of clusters to achieve sparse face representation with minimal redundancy.
The project, which was awarded a grant of $50,000, will begin on January 15 with a final deadline of June 30.