Abstract
In recent years, the approaches of human computer interaction (HCI) are in rapid improvement. There is rich information in the hand which can be used to accomplish complex interactions in HCI. Taking advantage of the depth information from Kinect, this paper defines some feature points in hand and furthermore presents a set of Kinect-based algorithms to detect and locate these points to fulfill hand recognition. Our algorithms include three steps: wrist recognition, palm center detection and fingertips localization. The innovative wrist recognition method proposed in this paper is used to separate the hand and forearm region and is based on distance transformation algorithm and the geometric feature of wrist. As for fingertip localization, we propose the θ-curvature algorithm, which overcomes the shortcoming of the former K-curvature algorithm on the parameter selection. Our experiment results demonstrate that wrist, palm center and fingertips can be located quickly and accurately by the hand feature points localization algorithm.
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.
