Towards New User Interfaces Based on Gesture and Sound Identification.

The average user communicates with the computer using a keyboard and a computer mouse. The keyboard remains at the core computer interaction since the first commercial computer in 1984. In more than half a century since the invention of the first computer mouse many pointing devices have been introduced, of which best known are a tracking mouse (trackball) and light pen. None of these devices worked out to be better than the keyboard, so the majority of human-computer interaction (HCI) is performed via computer keyboard and mouse, which are still the same as they were at the time of the invention. With the rapid advances of technology other ways of HCI were developed. In the last decade, a noticeable use of touch screen devices and other innovative gaming interfaces were developed and successfully used in practice. At the same time with technology development new challenges emerged, e.g. ”How to communicate with computers using complex commands without direct physical contact?” The solution would facilitate and optimize work in many specialized domains. Alexander Shpunt [Dibbell 2011] introduced three-dimensional (3D) computer vision. Simple communication and control of a computer by using the user’s movements (gestures) and voice commands was enabled. The sensing device records observed space, takes an image and converts it into a synchronized data stream. Data stream consists of depth data (3D vision) and color data (similar to human vision). Depth vision technology was invented in 2005 by Alexander Shpunt, Zeev Zalevsky, Aviad Maizels and Javier