A Comparative Analysis of Gesture Recording Technologies and Recognition Methods

Abstract

The dynamic development of computing techniques and communication tools and the improvement of network technology have increased the role of information as the main resource in society. The application of information communication technologies has stimulated the development of intellectual and scientific potential all over the world and has been successfully applied to all fields. Gestures are the only means of communication for hearing and speech impaired people. Automatic recognition of gestures in order to facilitate communication through gestures is an urgent issue from both scientific and practical point of view. This article highlights the static and dynamic gestures. The process of gesture recognition collects data by means of various sensor technologies. The article analyzes the image-based and non-image-based technologies and presents their advantages and disadvantages. It also comparatively analyzes the working principle of existing methods proposed for the gestures identification, explores their advantages and disadvantages and interprets the performance of the software which localizes the hand showing the gesture in the video frame. As a result, it develops a machine learning method based on neural networks for high accuracy identification of gestures. The developed method testing on database open for research shows high performance.