A dynamic gesture interface

• Main Author: Metais, Thierry
• Format: Others
• Language: en
• Published: University of Ottawa (Canada) 2013
• Subjects: Computer Science.
• Online Access: http://hdl.handle.net/10393/26983; http://dx.doi.org/10.20381/ruor-11857

Technological advancements during the last years made three dimensional virtual environments ubiquious computer applications. The traditional input devices such as keyboards and mice have reached their limits for they are no longer intuitive to manage 3 dimensional interactions. During the last decades, digital gloves were invented in an attempt to capture hand gestures. The work presented in this thesis is about recognizing hand shape based gestures for virtual environment navigation. We addressed this issue in two steps: first, we look for gesture representations that would allow a good discrimation between gestures; second, we have examined three strategies namely template matching, neural network and hidden Markov models to classify inputs suitably formatted. Experiments on classifying gesture samples with the three methods seem encouraging (more than 90 percent recognition), but when looking at real time gestural sequencee we conclude that only the Viterbi and neural network approaches should be used for a gesture interface.