OMRON

Global

  1. Home>
  2. Media Info.>
  3. News Releases - 2012>
  4. OMRON Develops Real-Time Facial Expression Estimation Technology

OMRON Develops Real-Time Facial Expression Estimation Technology

  • Text Size
  • Small
  • Medium
  • Large
  • October 23, 2012
  • FOR IMMEDIATE RELEASE

Kyoto, Japan - OMRON Corporation (TOKYO: 6645; ADR: OMRNY) today announced the development of new technology capable of estimating seven different facial expressions--happiness, surprise, fear, disgust, anger, sadness, and neutral--all in real time. The technology offers interesting possibilities in a variety of applications. If incorporated into a communication robot, for instance, the robot could react to a user's facial expressions. The technology is also ideal for image search engines, or interactive games that respond to the facial expressions of players.

OMRON's Facial Expression Estimation technology combines the company's proprietary 3D model-fitting technology1 and statistical classification method2, which is based on a massive database of facial images that OMRON has accumulated over many years. The technology has up till now been used primarily to recognize individual faces, but by enhancing these technologies it has become possible to also estimate facial expressions. Rather than relying on the detection of the shapes of individual facial parts such as the eyes and mouth, OMRON's technology estimates facial expressions based on the relative position of all facial parts, thus enabling high-speed estimation while requiring only a small amount of system memory. Since the process only requires a single facial image, real-time estimation of facial expressions is possible using not only video imagery but also still images.

In line with OMRON's ambition of "bringing machines closer to people," the company has been working on development of its "OKAO Vision" face detection technology since 1995. This facial image sensing technology is capable of detecting and extracting a wide range of information from facial images, and is now one of OMRON's core technologies. The developments to date have enabled such functions as Face Detection, Face Recognition, Smile Degree Estimation, Gaze and Blink Estimation, Eye Open-close Estimation, and Age and Gender Estimation. "OKAO Vision" technology is also used in the auto-focus function of digital cameras and smartphones, as well as the skin beautification function of printers, image management for personal computers, and many, many other applications.

The addition of the new facial expression estimation capabilities to "OKAO Vision" enables smoother communication and interaction between people and machines and will help to further expand the range of applications for the technology.

Real-Time Facial Expression Estimation Technology

Features

  1. Seven different expressions can be estimated--happiness, surprise, fear, disgust, anger, sadness, and neutral. By indicating the degree to which each expression is evident, even ambiguous expressions can be estimated.
  2. Because expressions can be estimated from a single facial image, this technology can be used with both still and video imagery and is therefore suited for use with a wide range of devices.
  3. High-speed data processing requiring only a small amount of system memory enables real-time estimation.

Specifications and Performance

Recommended face image size 64 pixels or higher
Detectable expressions Happiness, surprise, fear, disgust, anger, sadness, and neutral
Processing time Approx. 10ms (Clock speed: Snapdragon at 1.0GHz)
Compatible operating systems Windows XP/7, Android OS, iOS, etc.

Application Examples

  1. Robotics
    Robotics
    Robots can react to the facial expressions of users.

  2. Gaming
    Gaming
    Game avatars can mimic the facial expression of players in real time.

  3. Photo decoration
    Photo decoration
    Decorations that match the subject's facial expression can be added to photos automatically.

  4. Image search
    Image search
    Photos can be searched according to the facial expressions and retrieved instantly.

Notes

1 3D model-fitting technology
Technology for creating 3D face shape models based on a massive database of facial image samples and comparing the shape of subjects' faces with the models.
2 Statistical classification method
A technique for identifying the categories that certain data belongs to based on common features for that category. The common features are extracted from a massive database of facial image samples.
  • OKAO Vision and OKAO are registered trademarks or trademarks of OMRON Corporation in Japan and other countries.
  • Windows is a registered trademark of Microsoft Corporation in the United States and other countries.
  • Android is a trademark of Google Inc.
  • Other product and service names are trademarks or registered trademarks of respective owners.

For more information regarding OMRON's facial expression recognition technology, visit: http://www.omron.com/ecb/products/mobile/

About OMRON

Headquartered in Kyoto, Japan, OMRON Corporation is a global leader in the field of automation. Established in 1933, and headed by President Yoshihito Yamada, OMRON has more than 36,000 employees in over 35 countries working to provide products and services to customers in a variety of fields including industrial automation, electronic components, social systems, and healthcare. The company has five regional head offices in Kyoto (Japan), Singapore (Asia Pacific), Shanghai (Greater China), Amsterdam (Europe, Africa, and the Middle East), and Chicago (the Americas). For more information, visit OMRON's website: http://www.omron.com/

Sales Inquiries
OMRON Electronic and Mechanical Components Company
Application Oriented Components Department
Tel.: +81-77-565-5673
okao-vision@omm.ncl.omron.co.jp
Media Inquiries
OMRON Corporation
Arlo Cook, +81-3-6718-3430
Corporate Communications Department
arlo_cook@omron.co.jp

Top of Page