Skip to Content

CES: Face Recognition on the Fly

New mobile phone software recognizes your friends in real time.
January 7, 2011

While companies like Vuzix work on augmented reality hardware, Viewdle is working on the software side, demonstrating a face recognition system for mobile phones at the Consumer Electronics Show in Las Vegas. Using the phone’s camera, it can pick out faces and tag them with names on the fly; the goal is then to link these names with social networks and other online sources, so that their latest tweet or Linked In job title can appear beneath their image.

The primary challenge for the developers was creating a system that can work with the constrained memory, processing power, and low quality optics of mobile phones (phone manufacturers can increase the resolution of the imaging sensor but do little to improve the lens, typically resulting in more fuzzy pixels rather than better images.) The Viewdle software works by creating compressed “faceprints” that are stored in a database on the phone. These faceprints are created from multiple images to allow the system to recognize a face even when a person changes their expression or is seen at an angle.

Faceprints are created either directly from a few seconds of video of the person taken with the phone, or a user can give Viewdle access to the tagged pictures in their Facebook account. Viewdle will analyse these pictures remotely and send the user’s phone the correspoding faceprint database. Viewdle have been able to limit the processing requirements of their software to about 30 percent of the CPU power of a typical smartphone.

Mobile device makers Qualcomm and Blackberry are among Viewdle’s investors, and the company, which is headquartered in Palo Alto but does most of its research and development in Kiev, hopes that their software will start showing up in products by mid 2011.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.