A fingertip detection and tracking system as a virtual mouse, a signature input device and an application selector

Abstract

This paper presents vision-based fingertip detection and tracking system on a 2D plane using a camera as an input interface to the computer. An intensity based approach is used to detect the arbitrary shaped, uniform colored 2D area on which the hand operates, and then the fingertip is effectively detected and tracked using the sampled hand contour. Grid sampling approach is used for a fast implementation. The system achieves speeds of up to 30 fps. Tip pointers such as a stylus or a pen can be used in place of the fingertip, making the device user-friendly. The system is used to implement a virtual mouse, a signature input device and an application selector.