The best way to conference proceedings by Francis Academic Press

Web of Proceedings - Francis Academic Press
Web of Proceedings - Francis Academic Press

Research on Gesture Recognition Based on Convolutional Neural Network and SVM

Download as PDF

DOI: 10.25236/iciss.2019.017

Author(s)

Shoujin Wang, and Dongxu Li

Corresponding Author

Shoujin Wang

Abstract

In the new generation of human-computer interaction technology, gesture recognition is a very important research direction. Different from traditional gesture recognition methods, convolutional neural network can automatically perform feature extraction without manual intervention. In this paper, the method of combining a convolutional neural network and support vector machine is employed to gesture recognition, using the American Sign Language Data Set to train and test. Experiments show that the method has lower complexity and better recognition effect.

Keywords

Convolutional Neural Network, Support Vector Machine, Gesture Recognition