Abstract
An accelerometer is installed in most current mobile phones, such as the iPhones, Android-powered devices, and video game controllers for Wii or PS3, which enable easy and intuitive operations such as scrolling browsers and drawing 3D objects by detecting the inclination and motion of devices. Therefore, many gesture-based user interfaces with accelerometers are expected to appear in the future. Gesture recognition systems with accelerometers generally have to construct gesture models with user's gesture data before use, and recognize unknown gestures by comparing them with training data. As recognition process generally starts after the gesture has finished, output of the recognition result and feedback, e.g. scrolling, have a delay, which may cause users to retry gestures and degrade interface usability. We propose a method of early gesture recognition that calculates the distance between input data and training data sequentially, and outputs recognition results only when one output candidate has a stronger likelihood than the others. Additionally, we implemented a gesture-based photo viewer as an example of useful applications of our proposed method.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
