Performance Comparison of Three Different Classifiers for Hci Using Hand Gestures

Abstract

Abstract: With the ever-increasing diffusion of computers into the society, the present popular mode of interactions with computers (mouse and keyboard) will become a bottleneck in the effective utilization of information flow between the computers and the human. The use of hand gestures provides an attractive alternative to cumbersome interface for human-computer interaction (HCI). The hand can be used to communicate, with much more information by itself compared to computer mouse, joysticks, etc. allowing a greater number of possibilities for computer interaction. Developing new techniques for humancomputer interaction is very challenging, in order to use hands for interaction, it is necessary to be able to recognize them in images. In this paper, a robust hand gesture recognition system is presented for recognizing static gestures based on Zernike moments (ZMs) using Three Classifiers K-nearest Neighbour(KNN), Support Vector Machine (SVM) and Artificial Neural Network (ANN). The proposed system is able to recognize the gesture irrespective of the angles in which the hand gesture image is captured, which makes the system more flexible, and a comparative study is carried out to show which classifier works better in reorganisation of gestures. screen to select the next slide. Hand Gestures can be used for remote controls for television sets, stereos and room lights. Household robots could be controlled with hand gestures. In Human Computer interaction, to operate computer with hand gestures no accessories like gloves are needed. The approaches to implement Human-Computer Interaction using Hand Gestures are based on k-Nearest