Skip to main content
  1. Home
  2. Computing
  3. Legacy Archives

Google publishes patent for celebrity facial recognition

Add as a preferred source on Google

Google Logo 1024x426-2Just yesterday, Google executive chairman Eric Schmidt was saying that the company wouldn’t be developing a facial recognition database. Now, a patent has been published by the USPTO entitled: “Automatically Mining Person Models of Celebrities for Visual Search Applications”. The timing is bad considering all the negative press about Google lately.

The Google engineers state in the celebrity facial recognition patent that, by feeding a name list and images corresponding to an individuals name, they’ll be able to create an accurate biometric model for the celebrities: “Recognition is then performed based on precision and recall to identify the face images as belonging to a celebrity or indicate that the face is unknown.” Not only would image search return tagged photos but any image on the web with that target celebrity, which would be great for news publishers looking for fresh pictures. Great for paparazzi, maybe not so great for fan club members.

Recommended Videos

According to the patent, the database has already experimented with a list of 1,000 celebrities (out of a larger set of 30,000) which includes Barack Obama, Britney Spears, Prince Harry of Wales, Brad Pitt, Sarah Palin and her daughter Bristol. As of the time of the experiments, the system had a hard time hunting down clean images of less-notable celebrities such as Bristol Palin who kept popping up with images of her mother.

Other problems presented in the “Failure Cases” section include different names associated with the same target, such as the problem between “Prince Henry of Wales” and the more colloquial “Prince Harry” (the latter turning up more images). Also, the system had a hard time distinguishing between the faces of fashion designers, and the faces of those who wore the designer’s clothing or simply celebrities wearing sunglasses.


Jeff Hughes
Former Digital Trends Contributor
I'm a SF Bay Area-based writer/ninja that loves anything geek, tech, comic, social media or gaming-related.
Topics
Samsung Galaxy S26 Ultra’s cool privacy display could appear on the next MacBook Pro
The feature that stops strangers from snooping on your screen is coming to the Mac, and sooner than anyone expected.
MacBoo Pro on table

Apple’s upcoming M6 Pro and M6 Max MacBook Pros are quietly turning into the best laptops the company has ever made. We already knew about the new chipset, OLED panels, a brand-new design, and more. And now, Apple is reportedly borrowing one of Samsung's coolest features for the next MacBook Pro, and it might arrive a lot sooner than previously thought.

If you have been following the Samsung Galaxy S26 Ultra, you already know about its Privacy Display feature. For those who missed it, the feature can instantly darkens the screen from anyone looking at it from the side. The effect can cover the full screen or just a section of it. It is incredibly handy if you work in public spaces and handle sensitive information.

Read more
AI bots are a hit across the hotel biz, and if they feel creepy, you’re not alone: Study
Hotel booking chatbots are creeping out customers, but there's a simple fix that can make a difference.
Isometric Ai assistant and bubble speech, 3D illustration

If you have ever tried to book a hotel online and found yourself unsettled by the AI chatbot trying to help you, science has your back. New study from Texas A&M College of Agriculture and Life Sciences confirms that hotel booking chatbots are genuinely creeping people out, and it is actually hurting bookings.

What is giving hotel chatbots their creep factor?

Read more
Pope says AI must be disarmed and shouldn’t dominate humanity. We’re going the opposite way.
The Pope just dropped his first encyclical, and AI companies should probably read it.
Pope Leo XIV signing his first encyclical

Pope Leo XIV signed his first encyclical on May 15, the 135th anniversary of Pope Leo XIII's Rerum novarum. The document, Magnifica humanitas, was published on May 25 and addresses one of the defining challenges of our time: artificial intelligence and its impact on humanity.

The core message isn't anti-technology. The Pope is clear that technology is neither a threat nor inherently evil. However, he does say that technology is never neutral, because it takes on the values of those who build, fund, and control it. That's where things get interesting.

Read more