Hand gesture recognition using Kinect.

Human-computer interaction;Finger identification;Hand gesture recognition;Kinect

Yi Li, 1989-

University:University of Louisville

Department:Computer Engineering and Computer Science

关键词: Human-computer interaction;    Finger identification;    Hand gesture recognition;    Kinect;   

Others  :  https://ir.library.louisville.edu/cgi/viewcontent.cgi?article=1822&context=etd

美国|英语

来源: The Universite of Louisville's Institutional Repository

【 摘 要 】

Hand gesture recognition (HGR) is an important research topic because somesituations require silent communication with sign languages. Computational HGRsystems assist silent communication, and help people learn a sign language.In this thesis. a novel method for contact-less HGR using Microsoft Kinect forXbox is described, and a real-time HCR system is implemented with Microsoft VisualStudio 2010. Two different scenarios for HGR are provided: the Popular Gesture withnine gestures, and the Numbers with nine gestures. The system allows the users toselect a scenario, and it is able to detect hand gestures made by users. to identifyfingers, and to recognize the meanings of gestures, and to display the meanings andpictures on screen. The accuracy of the HGR system is from 84% to 99% with single handgestures, and from 90% to 100% if both hands perform the same gesture at thesame time. Because the depth sensor of Kinect is an infrared camera, the lighting conditions.signers' skin colors and clothing, and background have little impact on theperformance of this system. The accuracy and the robustness make this system aversatile component that can be integrated in a variety of applications in daily life.