Face Recognition of Blacklisted Visitors in Casinos

Omnigo Software

About Omnigo

Omnigo (Canada) offers the world's leading software solutions for public safety, incident reporting and security management.

Unwanted Visitor is one of the solutions that provides face recognition from the casino's blacklist and is installed in 350 casinos, including most casinos in Las Vegas.

website: omnigo.com

Problem

The company was looking for opportunities to improve recognition accuracy rates and reduce false positives in order to increase the efficiency of the Unwanted Visitor service. At the time of contacting 3DiVi, the Company used the other vendor's face recognition algorithm.

Solution

In early 2019, Omnigo Vice President began testing alternative face recognition algorithms, including 3DiVi.

March 8, 2019

Omnigo Vice President started testing 3DiVi algorithm on a database of 4,000 people and 700,000 test images. The preliminary results were encouraging and the client decided to move to the pilot stage on real data by integrating face recognition SDK into the security system of one of their Casino clients.

July 5, 2019

Client has completed testing of 3DiVi algorithm with one of Omnigo largest customers.

“

After testing on 1,05 million images of people entering two casinos over a two week period we compared the results with their previous vendor.

Previous vendor results

25 people recognized from a hotlist of 21,476 people
6,255 alerts were rejected

3DiVi Results (algorithm v7.3)

221 people recognized from a hotlist of 21,476 people
1,831 alerts were rejected

It turned out that in a two week test period with real patrons on a hotlist, 3DiVi algorithm found approx. 8 times as many people with 70% less false alarms.

Soren Frederiksen, Omnigo Vice President

November, 2019

“

The first phase of the live pilot has been completed successfully so the deployment of 3DiVi solution has been planned for the end of January, 2020.