The ability to spot faces from any angle, and even when partially occluded, has always been a uniquely human capability. Not any more.
Back in 2001, two computer scientists, Paul Viola and Michael Jones, triggered a revolution in the field of computer face detection. After years of stagnation, these guys’ breakthrough was an algorithm that could spot faces in an image in real time. Indeed, the so-called Viola-Jones algorithm was so fast and simple that it was soon built into standard point and shoot cameras.
Part of their trick was to ignore the much more difficult problem of face recognition and concentrate only on detection. They also focused only on faces viewed from the front, ignoring any seen from an angle. Given these bounds, they realised that the bridge of the nose usually formed a vertical line that was brighter than the eye sockets nearby. They also noticed that the eyes were often in shadow and so formed a darker horizontal band.
So Viola and Jones built an algorithm that looks first for vertical bright bands in an image that might be noses, it then looks for horizontal dark bands that might be eyes, it then looks for other general patterns associated with faces.
Detected by themselves, none of these features are strongly suggestive of a face. But when they are detected one after the other in a cascade, the result is a good indication of a face in the image. Hence the name of this process: a detector cascade. And since these tests are all simple to run, the resulting algorithm can work quickly in real-time.
But while the Viola-Jones algorithm was something of a revelation for faces seen from the front, it cannot accurately spot faces from any other angle. And that severely limits how it can be used for face search engines.
Which is why Yahoo is interested in this problem. Today, Sachin Farfade and Mohammad Saberian at Yahoo Labs in California and Li-Jia Li at Stanford University nearby, reveal a new approach to the problem that can spot faces at an angle, even when partially occluded. They say their new approach is simpler than others and yet achieves state-of-the-art performance.
Farfade and co use a fundamentally different approach to build their model. These guys capitalise on the advances made in recent years on a type of machine learning known as a deep convolutional neural network. The idea is to train a many-layered neural network using a vast database of annotated examples, in this case pictures of faces from many angles.
To that end, Farfade and co created a database of 200,000 images that included faces at various angles and orientations and a further 20 million images without faces. They then trained their neural net in batches of 128 images over 50,000 iterations.
The result is a single algorithm that can spot faces from a wide range of angles, even when partially occluded. And it can spot many faces in the same image with remarkable accuracy.
The team call this approach the Deep Dense Face Detector and say it compares well with other algorithms. “We evaluated the proposed method with other deep learning based methods and showed that our method results in faster and more accurate results,” they say.
What’s more, their algorithm is significantly better at spotting faces when upside down, something other approaches haven’t perfected. And they say that it can be made even better with datasets that include more upside down faces. “In future we are planning to use better sampling strategies and more sophisticated data augmentation techniques to further improve performance of the proposed method for detecting occluded and rotated faces.”
That’s interesting work that shows how fast face detection is progressing. The deep convolutional neural network technique is only a couple of years old itself and already it has led to major advances in object and face recognition.
The great promise of this kind of algorithm is in image search. At the moment, it is straightforward to hunt for images taken at a specific place or at a certain time. But it is hard to find images taken of specific people. This is step in that direction. It is inevitable that this capability will be with us in the not too distant future.
And when it arrives, the world will become a much smaller place. It’s not just future pictures that will become searchable but the entire history of digitised images including vast stores of video and CCTV footage. That’s going to be a powerful force, one way or another.
Ref: arxiv.org/abs/1502.02766 Multi-view Face Detection Using Deep Convolutional Neural Networks
View the original article here
document.write(calculate_time('29 Mar 2015, 18:16'));Samsung has recently showcased us the Galaxy S6 and S6 Edge in India. Both these devices are available in 32GB / 64GB / 128GB capacity and already on pre-order in India.
document.write(calculate_time('29 Mar 2015, 17:59'));Meerkat is reportedly getting ready to make some changes to its app in order to better compete with Periscope, the live streaming app that Twitter just scooped up earlier this month.
document.write(calculate_time('29 Mar 2015, 17:43'));HTC has let details of the One E9+ slip on its Chinese website, but something doesn't quite add up.
document.write(calculate_time('29 Mar 2015, 17:34'));Back at the Google I/O developer conference in June 2014, Google officially unveiled the Android One project, a program in which Google would work hand-in-hand with low-cost smartphone manufacturers in emerging markets.
document.write(calculate_time('29 Mar 2015, 17:30'));We answer the age-old question of whether you should build or buy your gaming rig.
document.write(calculate_time('29 Mar 2015, 16:00'));From Richey Edwards's love of John Madden's American Football to Massive Attack's Kick Off 2 addition.
document.write(calculate_time('29 Mar 2015, 15:30'));Cover the country properly before boasting about tiny pockets of lab-perfect 4G.
document.write(calculate_time('29 Mar 2015, 12:50'));Whilst VR inevitably dominated the company's F8 developer conference, Messenger Platform was a big move on the business front.
document.write(calculate_time('29 Mar 2015, 05:11'));World's first dual-curved glass display is almost here, and it's an idea that is here to stay.
document.write(calculate_time('28 Mar 2015, 20:30'));We venture to a galaxy far, far away to highlight the greatest Star Wars games to ever hit the PC. 
document.write(calculate_time('28 Mar 2015, 19:30'));We look at what pieces of virtual reality tech are likely to change PC gaming forever, and the problems some genres present to VR.
document.write(calculate_time('28 Mar 2015, 18:30'));And why Apple might have made a slghtly better running watch than we all thought
document.write(calculate_time('28 Mar 2015, 18:30'));Are there really any differences between the two technologies that aim to smooth your PC games?
document.write(calculate_time('28 Mar 2015, 18:00'));Remembering Ocean's surreal platformer through Amiga Power's 1991 review.
document.write(calculate_time('28 Mar 2015, 16:31'));These are the television shows you need to be watching on Amazon Prime right now.
document.write(calculate_time('28 Mar 2015, 16:08'));Talking the future of game design with some of the most important names in the business.
document.write(calculate_time('28 Mar 2015, 15:30'));And why Bloodborne has made me a loner.
document.write(calculate_time('28 Mar 2015, 15:30'));For years, Mac gaming has been almost an oxymoron - not really worth considering if your love of games extends beyond Football Manager. But things are changing.
document.write(calculate_time('28 Mar 2015, 15:20'));Star Citizen is a game of almost unfathomable scope, from the creator of the classic Wing Commander, Chris Roberts.
document.write(calculate_time('28 Mar 2015, 14:36'));If James Bond had an external hard drive in his Aston Martin, it would be the Seagate Seven.Load more