Printed from http://www.electronista.com

Facebook's DeepFace facial software nears human levels of accuracy

updated 03:35 pm EDT, Sat March 22, 2014

Research outlines strides in facial recognition through deep learning

Facebook has revealed in a research paper that it has discovered a way to match faces from two different photographs with 97.25 percent accuracy. The research has aided in the development of a software project called DeepFace, which only slightly trails the facial recognition measured average of a human by only 0.28 percent.

The increased accuracy comes at a rate nearly 25 percent higher compared to other software by a process of facial verification rather than recognition. Improvement in the rate of verification is independent of changes in angle of the face towards a camera or differences in lighting. "You normally don't see that sort of improvement," says Yaniv Taigman, one of the researchers on Facebook's AI team.

Analysis from MIT on the claims made in the research paper yields information on the changing algorithms in facial recognition through the use of deep learning. The process of deep learning, in which artificial intelligence learns patterns in data through a network of simulated neurons, creates a numerical description of a photographed face which has been reoriented to face forward with use of a 3D model of an averaged forward-looking face as a guide. If enough matches are generated after the photos being compared are found, the software indicates they must be the same.

Facebook was able to train the layers of neurons in the deep learning system by using a sample of the photos stored by the company. Approximately four million photos of faces from around 4,000 users were accessed in the process.

The software was developed by a team of four, including Taigman, Ming Yang and Marc'Aurelio Ranzato of Facebook's internal research department and Lior Wolf, a professor at Tel Aviv University. The software is currently only a research project, and there are no plans for it to be deployed for widespread use at this time. Findings of the paper will be presented at the IEEE conference on Computer Vision and Pattern Recognition in June.



By Electronista Staff
Post tools:

TAGS :

toggle

Comments

  1. robttwo

    Fresh-Faced Recruit

    Joined: 11-15-05

    ...and a new captcha spamming technology is born.

  1. kerryb

    Fresh-Faced Recruit

    Joined: 08-05-01

    Minority report is coming...

Login Here

Not a member of the MacNN forums? Register now for free.

toggle

Network Headlines

toggle

Most Popular

Sponsor

Recent Reviews

Plantronics Rig Surround 7.1 headset

Trying to capture the true soundscape of video games can be a daunting task. Looking to surround sound home theater options, users hav ...

Kenu Airframe +

Simple, stylish and effective, the Kenu Aiframe + portable car mount is the latest addition to Kenu's lineup. Released earlier this ye ...

Adesso Compagno X Bluetooth keyboard

The shift from typing on physical keyboards to digital versions on smartphones and tablets hasn't been an easy for many consumers. Fro ...

Sponsor

toggle

Most Commented

 
toggle

Popular News