期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：12
出版社：Journal of Theoretical and Applied
摘要：Internet of Things (IoT) is a promising computing model, which uses several enabling technologies to provide new type of smart services that allow users to interact with daily objects in a different way. Most of IoT services are invoked using touch screens and connected to Smartphones or tablets to enable a real-time connectivity between users and things. However, only a few IoT systems consider gesture based user interactions for their services which allow users to have a better experience with IoT products. In this work, we present a gesture recognition system for gesture control on IoT services. In particular, the gesture recognition system is based on alphabet characters and number to classify the hand fingertip trajectory using a hidden Markov model. The presented system composed of three key stages. Firstly, color information with 3D depth information that segment the correct position of hands. Then the fingertip is detected based on the curvature of hand contour. Secondly, the dynamic features in polar coordinates are employed using k-mean clustering technique. Finally, Baum-welch procedure is used to carry out the learning gestures and the viterbi algorithm is used to recognize the gesture. The experiments demonstrate that the presented system has a capability to classify the isolated gesture dues to spatio-temporal variability. Precisely, our experiment provides a promising result where the average recognition rates achieved 98.61% and 93.06% for training and testing dataset, respectively. Furthermore, it provides finer presentation and low-slung computational difficulty when functional image sequences samples of multipart circumstances are used.
关键词：Internet of things' services; gesture recognition; gesture control; color information; depth map; hidden Markov model.
