OMRON

Global

  1. Home>
  2. Media Info.>
  3. News Releases - 2012>
  4. OMRON Develops Hand Gesture Recognition Technology - Combination with Facial Image Sensing Technology Eliminates Need for User Prompting -

OMRON Develops Hand Gesture Recognition Technology
- Trigger Motion is Unnecessary by OKAO's Facial Image Sensing Technology -

  • Text Size
  • Small
  • Medium
  • Large
  • May 28, 2012
  • FOR IMMEDIATE RELEASE

Kyoto, Japan - OMRON Corporation today announced that the company has developed a new hand gesture recognition technology capable of simultaneously recognizing the position, shape, and motion of a person's hand or finger by referencing a camera-recorded image. By combining this technology with OMRON's core facial image sensing technology, gesture recognition can be started automatically based on the analysis of interrelation between the position or direction of the face and the hand shape or position. While conventional gesture recognition technologies require trigger motion for start the recognition process through an initial movement, such as waving a hand. OMRON technology does not require this, allowing more natural interaction with machines based on the interpretation of the user's intention.

Part of this technology will be released at the Symposium on Sensing via Image Information (SSII 2012) to be held in Pacifico Yokohama from June 6 to 8.

In recent years, gesture recognition has been attracting a great deal of attention as a natural human-machine interface. The technology allows users to control or manipulate devices in a more natural manner, such as operating a TV set by hand movements or releasing the shutter of a camera via a V-sign. OMRON's gesture recognition technology employs a statistical classification method1 and model-fitting technology2, both of which were developed through the company's accumulated expertise over many years. By the modeling of hand shapes, this new technology enables speedy recognition of gestures using a small amount of memory.

OMRON has been involved with technology developments for its "OKAO Vision" since 1995. This facial image sensing technology is capable of detecting various kinds of information from facial images, and is one of OMRON's core technologies. The developments to date have enabled such functions as face detection, face recognition, smile degree estimation, estimation of gaze direction, detection of the degree of mouth or eye opening, and estimation of age and gender. These developments led to the employment of "OKAO Vision" for 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 other applications.

OMRON will further advance its image sensing technology for detecting faces and recognizing human movements, aiming to create technology to correctly interpret the intention of users, such as judging what they are trying to do through the analysis of gestures.

position
position

shape
shape

motion
motion

Features

  1. Trigger motion is not necessary by facial image sensing technology.
  2. Hand or finger position, shape and movements can be recognized simultaneously.
  3. Hand gesture detection ranges from very near (about 10cm) to far (several meters).
  4. High-speed recognition is enabled on smartphones and tablets.
  5. Small program size makes it possible to embed the technology in a diverse range of devices.

Specifications and Performance

Recognizable size Size of hand, 40 pixels or higher
Recognizable motions Up, down, left, right
Recognizable hand/finger shape V-sign, etc.
Recognition start By hand-waving or automatic via combination of face and hand recognition
Recognition speed 30 frames/second, Operation clock: Snapdragon at 1.0GHz
Compatible operating systems Windows XP/7, Android OS, iOS, etc.

Application Examples

V-sign shutter
V-sign shutter

TV control
TV control

Notes

1 Statistical classification method
Technique for extracting specific hand features, such as common colors and shapes, from a massive amount of hand image samples.
2 Model-fitting technology
Technology for creating hand shape models based on a massive amount of hand image samples and comparing the shape of a particular hand against models.
  • 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.

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 at http://www.omron.com/

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

Top of Page