Research on A Gesture Recognition Method of Arc Curve

Gesture recognition is an important way of human-computer interaction, improving gesture recognition rate is of great significance for human-computer interaction applications. To solve the problems of few categories and low performance of gesture recognition in traditional methods, a new method of g...

Full description

Saved in:
Bibliographic Details
Published in2023 8th International Conference on Image, Vision and Computing (ICIVC) pp. 101 - 106
Main Authors Xing, Yiliang, Lei, Huajun
Format Conference Proceeding
LanguageEnglish
Published IEEE 27.07.2023
Subjects
curve
decision tables
Games
geometric feature
Gesture recognition
Human computer interaction
Image recognition
Robustness
Software
Technological innovation
Online AccessGet full text

Cover

More Information
Summary:Gesture recognition is an important way of human-computer interaction, improving gesture recognition rate is of great significance for human-computer interaction applications. To solve the problems of few categories and low performance of gesture recognition in traditional methods, a new method of gesture recognition based on circular arc curve is proposed in this paper. Firstly, the hand detection arc curve based on geometric characteristics of the hand is constructed. Then, key pixels intersecting with the curve are selected, clustered and are divided into different categories according to their spatial adjacency. Then spatial angle of key pixels is calculated by vectorial angle method. Finally, number and angle of the categories are used as gesture features, and gesture recognition is based on decision table. Experimental results show that the method has the characteristics of high recognition rate, high performance and good robustness.
DOI:10.1109/ICIVC58118.2023.10270388