Automated Face Analysis Gets Real

EE_Times-logo

By Brian Dipert
Editor-in-Chief, Embedded Vision Alliance

This blog post was originally published at EE Times' SoC Design Line. It is reprinted here with the permission of EE Times.

This week, I've invited my colleague Brian Dipert to share his perspective on various face analysis algorithms used in embedded vision. As Editor-in-Chief of the Embedded Vision Alliance, Brian regularly discovers and reports on interesting embedded vision applications, some of which he discusses here. — Jeff

Face recognition, the technology that enables cameras (and the computers behind them) to automatically, rapidly and accurately identify people, has become a popular topic in fictional movies and television. Consider, for example, the 2002 blockbuster Minority Report. If you've seen it (and if you haven't, you definitely should), you might recall the scene where Tom Cruise's character Chief John Anderton is traversing a shopping mall. Sales kiosks greet him by name, after identifying him by scanning his face, and solicit him with various promotions. Lest you think that this is just a futuristic depiction, British supermarket chain Tesco is now making it a reality.

Plenty of other real-life face recognition implementations currently exist. Consider "Tag Suggestions," the automated identification of friends' faces that Facebook undertakes each time you upload a photo to the service (a facility likely enhanced by the company's 2012 acquisition of Face.com), or the automated clustering of pictures containing the same person accomplished by Apple's iPhoto software. Don't forget about the face recognition-based "unlock" option supported in the last few Android releases (likely enabled by Google's 2011 acquisition of Pittsburgh Pattern Recognition), and available on iOS via third-party applications. And both the new Microsoft Xbox One and Sony PlayStation 4 game consoles support face recognition-based user login and interface customization, via their camera accessories (included with the Xbox One, optional with the PS4).

Face recognition has made substantial progress in recent years, but it's admittedly not yet perfect. Some of its limitations are due to an insufficiently robust database of images to compare against. And some of its limitations are the result of algorithms not yet able to fully compensate for off-center viewing angles or poor lighting, for example, or subjects that are wearing hats or sunglasses, or who sport new facial hair or makeup. Face recognition's current inability to identify people with guaranteed reliability provides privacy advocates with solace, ironically. However, other face analysis technologies are arguably more mature, enabling a host of amazing applications, and are also useful for addressing privacy concerns, since they don't attempt to identify individuals.

For example, face analysis algorithms can accurately discern a person's gender. This capability is employed by electronic billboards that display varying messages depending on whether a man or woman is looking at them, as well as by services that deliver dynamically updated reports on meeting-spot demographics. Face analysis techniques can also make a pretty good guess as to someone's likely age bracket. Intel and Kraft harnessed this capability last year in developing a line of vending machines that only dispense free pudding samples to adults. And more recently, Chinese manufacturing subcontractor Pegatron has begun using it to screen job applicants, flagging those who may be less than 15 years old as a means of avoiding hiring underage workers.

The mainstream press tends to latch onto any imperfection as a broad-brush dismissal of a particular technology. As engineers, we know how over-simplistic such an approach is. While R&D and product developers continue to pursue the holy grail of 100% accurate face recognition, other face analysis techniques are currently sufficiently mature to support numerous compelling uses. How will you choose to leverage them in your next-generation system designs? Visit the website of the Embedded Vision Alliance for plenty of application ideas, along with implementation details and supplier connections. And plan to attend the Alliance's next Embedded Vision Summit, a technical educational forum for engineers interested in incorporating visual intelligence into electronic systems and software, to be held in Santa Clara, California at the end of May.

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.

Contact

Address

Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596

Phone
Phone: +1 (925) 954-1411
Scroll to Top