Gesture recognition system for controlling iot systems

The development of the Internet of Things (IoT) opens up new opportunities for creating intelligent services that enhance user interaction with surrounding devices. Modern IoT systems primarily use touchscreens and mobile applications for control; however, gesture-based methods can significantly expand their functionality. This work proposes a gesture recognition system applied to the control of IoT devices. The core of the system is the classification of finger movement trajectories using a Hidden Markov Model (HMM). The system consists of three main stages: initial hand segmentation using colour and depth information, fingertip detection based on hand contours, and the use of clustering in polar coordinates to extract dynamic features. The Baum-Welch and Viterbi algorithms are applied for training and gesture recognition, respectively. Experimental results show that the developed system is capable of classifying gestures with consideration of spatiotemporal variability with high accuracy. In particular, the average recognition rate reached 98.61% for the training set and 93.06% for the test data. The proposed approach demonstrates effectiveness under challenging conditions, including changes in lighting and partial occlusion of objects in the scene.