Facebook’s new facial recognition project claims to match faces with 97.25 per cent accuracy. After three solid days of networking, presentations, and deal-making for the biometrics and identification community, the inaugural Connect:ID conference many biometric milestones where celebrated.
Almost two years ago, Facebook bought Face.com, an Israeli start-up that specialised in face-recognition software. Given the instant backlash, it’s no surprise Facebook has kept pretty quiet about the technology since then.
Last week, though, Facebook quietly published a research paper that shows it has in fact been hard at work developing its face-recognition capabilities. The paper, co-authored by Face.com co-founder Yaniv Taigman, introduces a system called DeepFace that can match two images of the same face with incredible accuracy.
Facial recognition technologies remain something of a taboo.
Trained on a data set of some 4 million photos “from a popular social network”, the software uses 3D modeling techniques and artificial neural networks to recognise similarities between two images of the same person – even when the angle, lighting, and facial expressions are different.
Just how good is DeepFace? On one benchmark data set, composed of professional photographs of thousands of different celebrities, it achieved an accuracy rate of 97.25 per cent. That’s almost exactly as accurate as your average human.
Taigman and his co-authors – Ming Yang and Marc’Aurelio Ranzato of Facebook’s artificial intelligence team and Lior Wolf of Tel Aviv University – plan to present DeepFace at a computer vision conference in June, MIT Technology Review reports.