Hand-free head mouse control based on mouth tracking
Authors:
- 1 July 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 707-713
Abstract
Hand-free control for human-computer interface has been very important nowadays. For hand-free solution, to use human body movement tracking in video input and utilize the tracking is an important kind of solution. In this paper, we have presented a hand-free head mouse control based on mouth tracking. Our system firstly nonlinearly transformed the input video frame of human head into YCbCr color space, then use the visible chrominance feature of face in this color space to detect human face region. And then for face candidate, use the nearly reversed relationship information between Cb and Cr cluster of face feature to detect mouth position. We use mouth position interval information between front-frame and the next-frame in video frames of head motion to confirm if a mouth tracking is movement information or command information, once a movement information has been determined, we use a mapping function which is set up by relationship between MMA and screen to map mouth position, then the real mouse position can be got, by this way we can operate mouse cursor in OS. On the other ways, if mouse click command information is determined, we can capture the mouth movement tracking, and then use recognition machine to recognize the tracking to determine which command it is. We have made experiments on Windows XP System to evaluate that our algorithm can represent a good effect for human-computer interface.Keywords
This publication has 10 references indexed in Scilit:
- The CMU pose, illumination, and expression databaseIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Perceptual user interfaces using vision-based eye tracking2003
- Face detection in color imagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- A fast and accurate face detector based on neural networksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Automatic analysis of facial expressions: the state of the artIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Unsupervised and adaptive Gaussian skin-color modelImage and Vision Computing, 2000
- Perceptual user interfaces (introduction)Communications of the ACM, 2000
- A Multilinear Singular Value DecompositionSIAM Journal on Matrix Analysis and Applications, 2000
- Frontal-view face detection and facial feature extraction using color, shape and symmetry based cost functionsPattern Recognition Letters, 1998
- What you look at is what you get: eye movement-based interaction techniques1990