OMRON Develops Hand Gesture Recognition Technology
OKAO's Facial Image Sensing Technology means Trigger Motion is Unnecessary
Kyoto, Japan - OMRON Corporation (TOKYO:6645)(ADR:OMRNY) 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 a trigger motion to start the recognition process, such as waving a hand, OMRON's technology does not require this, allowing more natural interaction with machines based on the interpretation of the user's intention.
Aspects of this new technology will be demonstrated 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 with hand movements or releasing the shutter of a camera via a hand gesture. 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. Through the modeling of hand shapes, this new technology enables speedy recognition of gestures using a small amount of memory.
OMRON has been involved with facial recognition with its "OKAO Vision" technology 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.
1. Trigger motion is not necessary thanks to 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.