Research Article
Proposing Gesture Recognition Algorithm Using HOG and SVM for Smart-Home Applications
@INPROCEEDINGS{10.1007/978-3-030-77424-0_26, author={Phat Nguyen Huu and Tan Phung Ngoc and Hoang Tran Manh}, title={Proposing Gesture Recognition Algorithm Using HOG and SVM for Smart-Home Applications}, proceedings={Industrial Networks and Intelligent Systems. 7th EAI International Conference, INISCOM 2021, Hanoi, Vietnam, April 22-23, 2021, Proceedings}, proceedings_a={INISCOM}, year={2021}, month={5}, keywords={Gesture recognition Histogram of oriented gradient Support vector machine Kernel correlation filter Convolution neural network}, doi={10.1007/978-3-030-77424-0_26} }- Phat Nguyen Huu
Tan Phung Ngoc
Hoang Tran Manh
Year: 2021
Proposing Gesture Recognition Algorithm Using HOG and SVM for Smart-Home Applications
INISCOM
Springer
DOI: 10.1007/978-3-030-77424-0_26
Abstract
Gesture recognition is one of the key aspects of robot communication systems. There are many image recognition techniques that are being developed to use in many different intelligent systems. In the paper, we perform the image processing techniques that include artificial intelligence technologies and deep learning in gesture recognition to apply for smart-home systems. We propose the gesture recognition model including the histogram of oriented gradient (HOG) and support vector machine (SVM) detection algorithms combining the kernel correlation filter (KCF) algorithm for tracking objects and a multi-layer convolution neural network (CNN) for classifications. The results show that the proposal algorithm is applicable for real environments with accuracy up to 99% per 6 seconds.
