Comparison of Algorithms for Dynamic Hand Gesture Recognition
Slavomír Kajan, Jozef Goga, Ondrej Zsiros · 2020
The aim of this work is to compare different algorithms for dynamic hand gesture recognition using the Kinect v2 sensor. We have developed an application that has implemented algorithms such as dynamic time warping algorithm, hidden Markov models, long short-term memory network and convolutional neural networks. To test and compare the mentioned algorithms, a simple database was created. Using our own database we have gained an objective way of comparing these algorithms.