期刊
IEEE ACCESS
卷 9, 期 -, 页码 157422-157436出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3129650
关键词
Gesture recognition; Assistive technologies; Data acquisition; Databases; Libraries; Human computer interaction; Object recognition; Classification; feature extraction; dynamic hand gesture recognition; sign language recognition; vision-based hand gesture; recognition accuracy
资金
- University Malaya Research Grant (UMRG) [RG284-14AFR]
- Fundamental Research Grant Scheme (FRGS) [FP062-2020]
This paper reviewed the research progress of sign language in vision-based hand gesture recognition system from 2014 to 2020, indicating an active field with focus on data acquisition, data environment, and hand gesture representation. Recognition accuracy varies between signer dependent and signer independent studies, with a lack of progress in continuous gesture recognition, suggesting the need for further improvement towards a practical vision-based gesture recognition system.
This paper reviewed the sign language research in the vision-based hand gesture recognition system from 2014 to 2020. Its objective is to identify the progress and what needs more attention. We have extracted a total of 98 articles from well-known online databases using selected keywords. The review shows that the vision-based hand gesture recognition research is an active field of research, with many studies conducted, resulting in dozens of articles published annually in journals and conference proceedings. Most of the articles focus on three critical aspects of the vision-based hand gesture recognition system, namely: data acquisition, data environment, and hand gesture representation. We have also reviewed the performance of the vision-based hand gesture recognition system in terms of recognition accuracy. For the signer dependent, the recognition accuracy ranges from 69% to 98%, with an average of 88.8% among the selected studies. On the other hand, the signer independent's recognition accuracy reported in the selected studies ranges from 48% to 97%, with an average recognition accuracy of 78.2%. The lack in the progress of continuous gesture recognition could indicate that more work is needed towards a practical vision-based gesture recognition system.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据