Biases in Facial Recognition Algorithms

Abstract:

The recent expansion in the availability, capability, and use of face recognition has been accompanied by assertions that demographic dependencies could lead to accuracy variations and potential bias.  NIST conducted tests to quantify demographic differences in contemporary face recognition algorithms. This talk will present the outcomes of the study published in the report – FRVT Part 3: Demographic Effects, providing details about the recognition process, where demographic effects could occur, specific performance metrics and analyses, empirical results, and recommendations for research into the mitigation of performance deficiencies.  Additionally, this talk will cover recent topics around face recognition, such as the impact of face recognition with face masks and face morphing.

Dial-In Information

https://morganstate.zoom.us/meeting/register/tZ0pdeuupz4uHdCJo0BaN7oLS5WRxgpBR5Yt

Thursday, November 12, 2020 at 11:00am to 12:30pm

Virtual Event
Event Type

Academics, Lectures & Presentations, Faculty & Staff, Research

Audience

Faculty & Staff, Students

Topic

Research

Cost

Free

Department
Division of Research & Economic Development, School of Computer, Mathematical and Natural Sciences, School of Engineering
Contact Person

Willie E. May

Contact Email

willie.may@morgan.edu

Contact Phone

443-885-4631

Subscribe

Recent Activity