|
Title:
|
EXTENDED NODES OF ARTIFICIAL NEURAL NETWORK FOR GESTURE RECOGNITION |
|
Author(s):
|
Hye Yeon Cho and TaeYong Kim |
|
ISBN:
|
978-989-8533-80-7 |
|
Editors:
|
Ajith P. Abraham, Jörg Roth and Guo Chao Peng |
|
Year:
|
2018 |
|
Edition:
|
Single |
|
Keywords:
|
Artificial Neural Network, HCI, Accelerometer, Gesture Recognition, Pattern Recognition |
|
Type:
|
Poster/Demonstration |
|
First Page:
|
249 |
|
Last Page:
|
251 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Hand gestures can easily express ideas to others and these hand gestures can be applied to various fields such as art, game, and smart home. In this study, we propose a method to improve recognition rate for various kinds of 3-dimensional hand gestures. We extract the features from the gesture data distribution by Mahalanobis distance and construct the feature nodes, and feature nodes are added to the input layer of a neural network. Experimental results show that the proposed method has better performance than the conventional artificial neural network. |
|
|
|
|
|
|
