Chinese finger language recognition based on deep learning

Tao Zhang; Fuming Zhang

doi:10.1117/12.2639680

19 October 2022 Chinese finger language recognition based on deep learning

Tao Zhang, Fuming Zhang

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 122943O (2022) https://doi.org/10.1117/12.2639680
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

The study of hand gesture recognition has significant academic value and wide application prospects, but the accuracy of hand gesture recognition is affected by differences in environment, skin color, and hand shape. In this paper, we first preprocess the dataset, obtain the key points of the hand through the MediaPipe framework, and draw these key points on white pictures to form a new dataset, and then train the unpreprocessed dataset and the preprocessed dataset separately using the ResNet50 network structure. The results of the comparison experiments show that the accuracy obtained from the preprocessed dataset is 1.9% higher than that of the unpreprocessed dataset.

Citation Download Citation

Tao Zhang and Fuming Zhang "Chinese finger language recognition based on deep learning", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 122943O (19 October 2022); https://doi.org/10.1117/12.2639680

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available