Facial recognition technology is growing in popularity seemingly by the minute. More and more, it’s becoming valuable to use people’s facial features and data to learn about them and differentiate them from others, whether it’s an airport trying to heighten its security, a law enforcement agency cracking down on crime, or even an entertainment venue trying to ensure safety and minimize losses.
But one common question we hear is, “How accurate is facial recognition?” The technology analyzes several points on every person’s face, allowing you to compare one image to thousands of others and tell the difference between an average Joe and a potential criminal. Still, as experts in the industry, we know there are a few flaws to overcome. We’ll explore how accurate facial recognition is, and specifically shine a light on how accurate it is across races.
Facial Recognition Accuracy
So how accurate is facial recognition, anyway? Broadly speaking, facial recognition technology is 99 percent accurate. But our industry as a whole has more work to do to secure that extra percentage point. That’s because there are a few demographic blindspots.
NIST Algorithm Study
In 2019, the National Institute of Standards and Technology (NIST) evaluated 189 software algorithms from 99 developers. The primary goal was to learn how well each algorithm performed two essential face recognition tasks: one-to-one and one-to-many matching.
One-to-one matching confirms when a photo matches a different photo of the same person—for verification purposes, such as unlocking a smartphone. One-to-many matching, by contrast, looks at whether an image of someone matches anyone in a database—for identifying persons of interest.
Using 18 million images of 8.5 million people from the State Department, Department of Homeland Security, and FBI databases, NIST examined false positives and false negatives—the two types of errors facial recognition systems can make. A false positive happens when software misidentifies photos of two different individuals as depicting the same person. On the other hand, a false negative happens when software fails to match two photos that show the same person.
With such a robust catalog of images, NIST represented an array of demographics across the study, including:
Race or birth country
As a result, researchers uncovered trends in rates of false positives and false negatives across demographics. The study revealed five notable trends, listed below in the study’s words:
One-to-one matching: False positives occur more frequently for Asian and African American faces relative to images of Caucasian faces, with error differentials ranging from 10-100 between algorithms.
U.S.-developed algorithms: American Indians have the highest rates of false positives.
Asian-developed algorithms: There’s little difference in false positives in one-to-one matching between Asians and Caucasians.
One-to-many matching: African American females have higher rates of false positives.
False positives across demographics aren’t consistent in one-to-many matching between algorithms.
NIST’s study clearly shows demographic areas that warrant a closer look and suggest there is a need for improvement in the technology. But with so many facial recognition tools available, the study also highlights an important fact: Different algorithms perform differently.
How Accurate Is Facial Recognition by eConnect?
At eConnect, we know facial recognition is only valuable when it is highly accurate. That’s why we’ve worked tirelessly over the years to hone and perfect our technology for the gaming industry.
eConnect’s facial recognition and identity management tools account for differences across demographics such as race, gender, age, and more.
And we continue to refine and improve our systems every day. eConnect is the only platform on the market to successfully associate transactional data with faces. Our software helps users recognize an unlimited number of individuals by integrating with more big-box systems than anyone else in the industry.
eConnect taps into your existing cameras and ticket in, ticket out (TITO) systems, player ratings, and POS systems to assess activities and transactions against facial data. The platform performs:
Working in tandem with your existing systems, we provide accurate facial recognition solutions that start at the parking lot and extend beyond your entrance and across your venue’s floor.
eConnect is the best facial recognition software.
Our software was recently recognized by Gaming & Leisure (G&L) with the Platinum Award at the 2021 Annual Gaming & Hospitality Industry Awards, and for good reason. In addition to our commitment to innovation, devotion to industry transformation, superior customer service, and unparalleled casino integrations, our platform is more robust than anything else on the market. You get features like:
License plate recognition to tie vehicle license plates to enrolled patrons
ID scanning and enrollment of all patrons at the point of entry
Biometrics to automatically identify and notify security teams about troublemakers
VIP detection to identify high-value patrons
AML forensics to aid compliance officers and law enforcement officers
Self-exclusion module to stop self-excluded individuals from gaming
Mobile alerts to send notifications to your team, anytime and anywhere
Get the No. 1 Rated Facial Recognition Platform
There’s no doubt that facial recognition technology can—and should—keep growing. Our industry is still relatively new. It’s hard to remember how far technology has come when you live with it every day. Remember—your laptops and mobile devices stem from those old and clunky PCs of the ‘80s!
While some of the biggest challenges for the facial recognition and surveillance industry surround accurate IDs across racial lines, the best minds in the industry are working to break down these barriers. Need a proven solution for your venue? Trust eConnect. Learn more about facial recognition and identity management, and get in touch with one of our experts to discuss how to enhance your operation.