Picking faces out of a crowd is something humans are hardwired to do, but training computers to act in the same way is much more difficult.
There have been various breakthroughs in this field in recent months, but the latest could be the most significant yet.
Researchers from Yahoo Labs and Stanford University have developed an algorithm that can identify faces from various different angles, when part of the face is hidden and even upside down.
At the moment, the so-called Deep Dense Face Detector doesn’t recognise who the individual faces belong to, just that there is a face.
But the technology has the potential to be trained in this way.
The algorithm was built by Sachin Farfade and Mohammad Saberian at Yahoo Labs in California and Li-Jia Li at Stanford University.
It built on the Viola-Jones algorithm which spots front-facing people in images by picking out key facial features such as a vertical nose and shadows around the eyes.
By collecting these markers, the algorithm is able to determine if an image contains a face or not.
But, this did not account for faces that have been obscured, are looking in various directions, or were upside down.
With this in mind, Mr Farfade and his team used a form of machine learning known as a deep convolutional neural network.
This involves training a computer to recognise elements of images from a database using various layers.
Google used a similar technique for its recent GoogLeNet classification algorithm that can identify images within images, such as a hat on the head of a dog sat on a bench.
Mr Farfade trained his algorithm using a database of 200,000 images featuring faces shown at various angles and orientations, plus 20 million images that didn’t contain faces.
In their paper, the researchers said: ‘In this paper we propose a method based on deep learning, called Deep Dense Face Detector.’
‘It has minimal complexity…and can get similar or better performance [than other systems] while it does not require annotation or information about facial landmarks.’
And, the team said the technology could be improved following further training.
The Latest on: Facial recognition
via Google News
The Latest on: Facial recognition
- Worldwide Facial Recognition Markets to 2024 - Government & Defense Sector Among Verticals to Gain Maximum Tractionon July 5, 2019 at 9:20 pm
Dublin, July 05, 2019 (GLOBE NEWSWIRE) -- The "Facial Recognition Market by Component (Software, Tools, and Services), Application Area (Emotion Recognition, Attendance Tracking and Monitoring ... […]
- 3 Things: The reliability of facial recognition technologyon July 5, 2019 at 9:03 pm
1 Julian Price Pl. Charlotte, NC 28208 (704) 374-3500 ... […]
- You Can Opt Out of Using Facial Recognition to Board a Flighton July 5, 2019 at 6:46 pm
A few months ago during a layover in Atlanta, I came across an unusual sight: facial recognition being used in the boarding process. The technology, which is currently in beta testing for ... […]
- Biased and wrong? Facial recognition tech in the dockon July 5, 2019 at 1:01 pm
Police and security forces around the world are testing out automated facial recognition systems as a way of identifying criminals and terrorists. But how accurate is the technology and how easily ... […]
- The Met's facial recognition tech is still wildly inaccurateon July 5, 2019 at 6:01 am
THE MET POLICE is facing renewed calls to suspend its use of facial recognition technology after a report found that four out of five people identified as possible suspects were innocent. While this ... […]
- UK police's facial recognition system has an 81 percent error rateon July 4, 2019 at 12:00 pm
But officials inside the Metropolitan Police say otherwise. Facial recognition technology is mistakenly targeting four out of five innocent people as wanted suspects, according to findings from the ... […]
- Over 80% of facial recognition suspects flagged by London's Met Police were innocent, report sayson July 4, 2019 at 7:16 am
A new independent report claims that 81% of suspects flagged by facial recognition technology used by London's Metropolitan Police were innocent. The study was commissioned by Scotland Yard and ... […]
- London Police Facial Recognition ‘Fails 80% Of The Time And Must Stop Now’on July 4, 2019 at 6:12 am
Facial recognition technology in use in Leicester Square, London. Kirsty O'Connor/PA Images via Getty Images London’s Metropolitan Police’s controversial trial of facial recognition technology to spot ... […]
- London police’s face recognition system gets it wrong 81% of the timeon July 4, 2019 at 4:58 am
The first independent evaluation of the Metropolitan police’s use of face recognition warned it is “highly possible" the system would be ruled unlawful if challenged in court. The news: London’s ... […]
- Police face calls to end use of facial recognition softwareon July 3, 2019 at 11:00 am
Analysts say facial recognition systems regularly misidentified people. Photograph: Mark Kerrison/Alamy Stock Photo Police are facing calls to halt the use of facial recognition software to search for ... […]
via Bing News