Real Time Hand Pose Recognition Using Orientation Histogram Data in Hand Pose Space
This thesis explains about algorithm which cognize hand appearance in real time using only image without adhering separate sensor. Hand recognizes using edge directional histogram which comes under a constant quantity of 2 dimensional appearances because hand appearance is intricate. This method suit hand pose recognition in real time because it extracts hand space accurately, has little computation quantity, and is less sensitive to lighting change using color information in complicated background. Method which reduces recognition error using chief element analysis method to can recognize through hand shape presentation direction change is explained. A case that hand shape changes by turning 3dimensionally also by using this method is possible to recognize. Besides, chief element space creation time is reduced remarkably because edge directional data is used not image in time of analyzing chief element. Human interface system manufacture technique which controls a home electric appliance or game using suggested method at experience can be applied.
Jong-Min Kim Hwan-Seok Yang Seung-Jung Wi Jong-Pil Jeong Won -Bae Kim Woong-Ki Lee
Computer Science and Statistic Graduate School.Chosun.Univ. Dept.of information Telecommunication, Cheongam College. Dept.of Electrical Engineering, Songwon College. Computer Science and Statistic College of Natural Sciences.Chosun.Univ.
国际会议
首届嵌入式软件与系统国际会议(Proceedings of the First International Conference on Embedded Software and System)
杭州
英文
456-465
2004-12-09（万方平台首次上网日期，不代表论文的发表时间）