Artificial Intelligence

Identity Verification Using Face Recognition Improved by Managing Check-in Behavior of Event Attendees

When:
Wednesday, February 19, 2020, 2:00pm - 2:30pm PSTiCal
Where:
Conference Room 1016
This event is open to the public.
Type:
AI Seminar
Speaker:
Akitoshi Okumura, PhD
Video:
TBD
Description:

Identity-verification systems have been required to prevent illegal resale such as ticket scalping. The problem in verifying ticket holders is how to simultaneously verify identities efficiently and prevent individuals from impersonating others at a large-scale event at which tens of thousands of people participate. We previously developed Ticket ID system for identifying the purchaser and holder of a ticket. This system carries out face recognition after attendants check-in using their membership cards. The average face recognition accuracy was 90%, and the average time for identity verification from check-in to admission was 7 seconds per person. The system was proven effective for preventing illegal resale by verifying attendees of large concerts; it has been used at more than 100 concerts. The problem with this system is regarding face-recognition accuracy. This can be mitigated by securing clear facial photos because face recognition fails when unclear facial photos are obtained, i.e., when event attendees have their eyes closed, are not looking directly forward, or have their faces covered with hair or items such as facemasks and mufflers.

We propose a system for securing facial photos of attendees directly facing a camera by leading them to scan their check-in codes on a code-reader placed close to the camera just before executing face recognition. The system also takes two photos of attendees with this one camera after an interval of about 0.5 seconds to obtain facial photos with their eyes open. The system achieved 93% face-recognition accuracy with an average time of 2.7 seconds per person for identity verification when it was used for verifying 1,547 attendees of a concert of a popular music singer. The system made it possible to complete identity verification with higher accuracy with shorter average time than Ticket ID system.

 

Bio: Akitoshi Okumura received his B.E. and M.E. degrees in precision engineering from Kyoto University, Kyoto, Japan in 1984 and 1986. He joined NEC Corp. in 1986 for researching natural language processing, speech translation, and AI robots at Central Research Laboratories. He was a visiting scientist at USC/ISI in 1993. He received his Ph.D. in computer science from Tokyo Institute of Technology, Tokyo, Japan in 1999.

He is Vice Chairman of Information-technology Promotion Agency, Japan. He is IPSJ (Information Processing Society of Japan) Fellow.

He is the recipient of the 2010, 2015, and 2016 Field Innovation Awards from Japanese Society of AI, 2008 Kiyasu Special Industrial Achievement Award, 2017 Industrial Achievement Award, 2017 Yamashita SIG Research Award, and DICOMO2019 Best Paper Award from IPSJ.

« Return to Events