Computing At The Snap Of Your Fingers
Gesture-based computing sounds like fun. But it can actually be the difference between life and death in certain situations.
User-friendly gesture-based interface devices are widely perceived to enhance a system’s usability, i.e., the ease, convenience and hence interest in using it. However, the real benefits of gesture-based computing become far more evident in situations where touch-free operations are critical for the success of a procedure.
If you want to use a PC, wave your hand
Here’s an example—imagine a neurosurgeon performing a complex operation on a patient. During the procedure, the surgeon requires to refer to the patient’s MRI images, which have been loaded onto a computer in the operation theatre. Let’s assume that a particular image is required to be zoomed into. If the surgeon uses the system by touching the screen, keyboard or mouse, it could very well compromise sterility, and by spreading infection, adversely affect the outcome of the operation. Instead, what if the surgeon could simply gesture to the computer to zoom into the image Microsoft MCTS Training?
A hand gesture recognition system is exactly what researchers at Ben-Gurion University of the Negev (BGU) in Israel and the Institute of Medical Informatics (IMI), USA, have developed. What’s more, their hand gesture recognition system, Gestix, was successfully implemented in an actual ‘in vivo’ neurosurgical brain biopsy conducted at the Washington Hospital Center in Washington, DC, earlier this year.
An outcome of two years of joint R&D, {quotes}Gestix enables surgeons to manipulate or browse digital images during a medical procedure by gesturing to the machine.{/quotes} Dr Juan Wachs spent a year at the International Management Institute (under Dr Michael Gillam who conceived the project) as a research intern during his PhD studies at BGU. He explains that the gestures for this sterile gesture interface are captured by a Canon VC-C4 camera positioned above a large flat screen monitor, which is connected to an Intel Pentium system with a Matrox Standard II video-capturing device.
The camera is a key component of the Gestix system. In fact, Helman Stern, principal investigator on the project, professor, Department of Industrial Engineering and Management, BGU, says finding a cheap webcam that could operate under variable lighting conditions with their hand detection and segmentation algorithm, was the greatest difficulty the project team faced. Apparently, as most webcams have automatic adjustments for dim light conditions, the team decided to use a more professional camera.
Training a hand-gesture recognition system
Stern explains how Gestix functions: “In the first calibration stage, the machine recognises the surgeon’s hand gestures. Subsequently, surgeons must learn to implement eight navigation gestures, by rapidly moving the hand away from a ‘neutral area’ and back again. Gestix users even have the option of zooming in and out by moving the hand clockwise or counterclockwise. In order to avoid sending unintended signals, users may enter a ‘sleep’ mode by dropping the hand MCITP Certification.”