Feeds

Boffins claim machines now beat humans at face-matching

On the Internet, GaussianFace knows you're a dog

Secure remote control for conventional and virtual desktops

A pair of Hong Kong researchers is claiming a first, developing software that can identify people from photographs better than humans can.

Their claim, in this Arxiv paper, is based on the LWF – Labelled Faces in the Wild – benchmark. That benchmark comprises 13,000 photos of 6,000 public figures, with both humans and computers asked to compare pairs of photos and work out whether they're the same person.

According to researchers Chaochao Lu and Xiaoou Tang of the Chinese University of Hong Kong, humans perform the face-verification task with 97.53 per cent accuracy – which their approach, dubbed GaussianFace, beats at 98.52 per cent.

What Lu and Tang did was to look at existing face verification systems, which work either by building classification models or by extracting low-level features from the photos. Each approach has its shortcomings – chiefly because they need a fair amount of operator intervention to fine-tune how the software works, and because often multiple “training runs” are needed to work out which parameters need to be tuned.

Instead, in GaussianFace, Lu and Tang claim that they've produced a more computationally-efficient approach that works on a single training run, based on the Gaussian Process, “a non-parametric Bayesian kernel method”.

More simply: GaussianFace normalises each pic into a 150x120 pixel image, and uses five landmarks – two eyes, the nose, and the corners of the mouth – as the basis for the image transform. It then creates 25 x 25 overlapping tiles in the image, and captures a vector of each patch.

The other key to making GaussianFace work is to pick the right training dataset, according to the Arxiv Blog. For this, the researchers used LifePhotos and Multi-PIE datasets, which include the same subjects photographed under different conditions, so that the software could “learn” what the same face looks like under different illumination and viewpoints.

GaussianFace isn't perfect, however: “it still takes a long time to train our model for the high performance. In addition, large memory is also necessary. Therefore, for specific application, one needs to balance the three dimensions: memory, running time, and performance”, the researchers write.

“Surpassing the human-level performance may only be symbolically significant”, they note. ®

Choosing a cloud hosting partner with confidence

More from The Register

next story
Microsoft on the Threshold of a new name for Windows next week
Rebranded OS reportedly set to be flung open by Redmond
'In... 15 feet... you will be HIT BY A TRAIN' Google patents the SPLAT-NAV
Alert system tips oblivious phone junkies to oncoming traffic
Apple: SO sorry for the iOS 8.0.1 UPDATE BUNGLE HORROR
Apple kills 'upgrade'. Hey, Microsoft. You sure you want to be like these guys?
SMASH the Bash bug! Red Hat, Apple scramble for patch batches
'Applying multiple security updates is extremely difficult'
'Google is NOT the gatekeeper to the web, as some claim'
Plus: 'Pretty sure iOS 8.0.2 will just turn the iPhone into a fax machine'
ARM gives Internet of Things a piece of its mind – the Cortex-M7
32-bit core packs some DSP for VIP IoT CPU LOL
'People have forgotten just how late the first iPhone arrived ...'
Plus: 'Google's IDEALISM is an injudicious justification for inappropriate biz practices'
prev story

Whitepapers

Providing a secure and efficient Helpdesk
A single remote control platform for user support is be key to providing an efficient helpdesk. Retain full control over the way in which screen and keystroke data is transmitted.
Intelligent flash storage arrays
Tegile Intelligent Storage Arrays with IntelliFlash helps IT boost storage utilization and effciency while delivering unmatched storage savings and performance.
Beginner's guide to SSL certificates
De-mystify the technology involved and give you the information you need to make the best decision when considering your online security options.
Security for virtualized datacentres
Legacy security solutions are inefficient due to the architectural differences between physical and virtual environments.
Secure remote control for conventional and virtual desktops
Balancing user privacy and privileged access, in accordance with compliance frameworks and legislation. Evaluating any potential remote control choice.