Skin Color-Based Video Segmentation under Time-Varying Illumination
IEEE Transactions on Pattern Analysis and Machine Intelligence
Evaluating performance and acceptance of older adults using freehand gestures for TV menu control
Proceedings of the 10th European conference on Interactive tv and video
| Hi-index | 0.00 |
We present a development of a gesture-based interface for the elderly and people with mobility impairment in a smart house environment. To reduce a burden of memorizing a variety of gesture commands, we introduce baby signs which are natural and easy-to-remember body signs without special education. The baby signs can be applied not only to communicate with others but also to interact with a computer for people with low level of proficiency in conventional peripherals. To achieve this purpose, we have attempted to create a real application working under illumination change and real-time requirement. The system observes the user's sign by a monitor-mounted camera and color gloves. Introducing a robust hand segmentation method against illumination change and adopting HMMs, our initial result shows 94.33% success rate for 6 sign words.