Feeds

Boffins claim machines now beat humans at face-matching

On the Internet, GaussianFace knows you're a dog

The essential guide to IT transformation

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. ®

The essential guide to IT transformation

More from The Register

next story
BBC: We're going to slip CODING into kids' TV
Pureed-carrot-in-ice cream C++ surprise
China: You, Microsoft. Office-Windows 'compatibility'. You have 20 days to explain
Told to cough up more details as antitrust probe goes deeper
Linux turns 23 and Linus Torvalds celebrates as only he can
No, not with swearing, but by controlling the release cycle
Scratched PC-dispatch patch patched, hatched in batch rematch
Windows security update fixed after triggering blue screens (and screams) of death
This is how I set about making a fortune with my own startup
Would you leave your well-paid job to chase your dream?
prev story

Whitepapers

Endpoint data privacy in the cloud is easier than you think
Innovations in encryption and storage resolve issues of data privacy and key requirements for companies to look for in a solution.
Implementing global e-invoicing with guaranteed legal certainty
Explaining the role local tax compliance plays in successful supply chain management and e-business and how leading global brands are addressing this.
Advanced data protection for your virtualized environments
Find a natural fit for optimizing protection for the often resource-constrained data protection process found in virtual environments.
Boost IT visibility and business value
How building a great service catalog relieves pressure points and demonstrates the value of IT service management.
Next gen security for virtualised datacentres
Legacy security solutions are inefficient due to the architectural differences between physical and virtual environments.