Development of a gesture-based system of interaction with the interface of adaptive information systems

Abstract

The implementation of gesture control is an actual direction in the field of organizing interaction with adaptive information systems. This study considers the development of a neural network-based gesture control system for hand recognition and gesture classification. When implementing such systems, it is necessary to ensure the maximum accuracy of gesture recognition, as well as high performance (video stream processing speed). At the first stage of the study, the task of optimizing gesture control system was posed, including analysis of the information processing algorithms used for optimization according to the criteria of classification accuracy and performance. In the course of solving the optimization problem, the structure and parameters of the neural network were determined that provide the best accuracy indicators, and the necessary changes were made in the software of the gesture control system to achieve the required level of performance. The developed software for the gestural interaction system was tested when integrating with the interface of adaptive information systems implemented on the basis of the Unity game engine. The results obtained can be used in the implementation of interfaces for interaction with virtual reality with a high level of immersion.