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
[google_news title=”” keyword=”Facial recognition” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Facial recognition
- More than 6,000 fans use new facial recognition entry into Minute Maid Park for 2024 MLB Opening Dayon March 28, 2024 at 6:45 pm
The Houston Astros told ABC13 that about 6,000 fans participated in MLB Go-Ahead Entry to enter Minute Maid Park for Thursday's opening day game against the New York Yankees.The program allows users ...
- DOJ says interim facial recognition policy prioritizes First Amendment rightson March 28, 2024 at 2:00 pm
After passing on an opportunity to testify in front of the Commission on Civil Rights, the DOJ released written testimony that it submitted to the commission.
- Quebec insurance portal re-launches facial recognition program to organize photo bankon March 28, 2024 at 10:14 am
The registry is bringing back its facial recognition program, which was suspended last year – this time, to tidy up its biometric image database.
- Israel is using facial recognition technology to pinpoint Hamas terrorists in Gaza, reports sayon March 28, 2024 at 7:24 am
Israeli military intelligence is reportedly using facial recognition technology to monitor, identify and detain Hamas terrorists in the Gaza Strip.
- Israel reportedly using facial recognition and Google Photos to conduct mass surveillance in Gazaon March 28, 2024 at 6:54 am
The New York Times' reports that the program is "collecting and cataloging the faces of Palestinians" without their consent.
- Facial recognition endangers us all without a clear legal basison March 28, 2024 at 1:28 am
Technology researcher Stephanie Hare outlines the growing danger of the UK’s failure to legalise and regulate facial recognition technology ...
- Israel quietly rolled out a mass facial recognition program in the Gaza Stripon March 27, 2024 at 8:11 pm
Israel has deployed a mass facial recognition program in the Gaza Strip, creating a database of Palestinians without their knowledge or consent, The New York Times reports. The program, which was ...
- Astros go high-tech to allow fans to enter ballpark with facial recognition technologyon March 27, 2024 at 9:50 am
Fans with the new MLB Go-Ahead Entry can now bypass the long lines and breeze into the ballpark without even showing a ticket.
- Facial recognition technology will allow Astros’ fans to get into games fasteron March 27, 2024 at 9:12 am
Recommended Videos First introduced last season at Citizens Bank Park in Philadelphia, the Go-Ahead Entry system uses facial authentication technology to allow ticket holders who have chosen to use ...
- Israel Deploys Expansive Facial Recognition Program in Gazaon March 27, 2024 at 2:00 am
The experimental effort, which has not been disclosed, is being used to conduct mass surveillance of Palestinians in Gaza, according to military officials and others.
via Bing News