Cursor Control Using Head and Hand Movement

Abstract

Head tracking systems can be used for controlling a mouse cursor on a computer system. Open-source projects which use such an approach require that the user holds his/her head still during and after a calibration procedure, as even the slightest head movements could affect the system function in an undesirable way. An Image processing system for mouse cursor control was developed, which uses a front camera to compensate head movements during eye tracking. An alternative is to include the usage of various sensors and hardware devices are very costly and not user friendly. So a new system was introduced in which the camera is used to capture the images of the users and compare it with a trained set of data and using the head movement a corresponding motion of the mouse is defined. This approach is not only user friendly but also cost effective. The software part of the system is integrated into the openCV platform as a plugin. The openCV platform is a project under development, with the goal to provide a new definition to computer vision. A machine learning technique called cascade classifier is used in the training. Though the system is easy and low cost, a large training is required and initial usage may find some difficulty.