Chinese Journal of Liquid Crystals and Displays, Volume. 38, Issue 9, 1198(2023)
Method for improving the accuracy of 3D light field interaction based on a small dataset of hand key points using an MLP network
Fig. 7. Normalization affects the comparison results of recognition accuracy
Fig. 8. 3D light field human-computer interaction and display.（a）Artifact model；（b）Monkey head model.
Table 1. Simple gesture recognition results
View tableView in ArticleTable 1. Simple gesture recognition results
测试序列 种类 数量 正确率/% 时间/s 手势0 1 2 623 96.683 0.7 手势1 1 1 697 96.405 0.6 手势2 1 2 330 95.322 0.7 手势3 1 2 259 98.318 0.7 手势4 1 2 316 97.409 0.7 手势5 1 1 741 96.094 0.6 手势6 1 1 851 98.271 0.6 手势7 1 1 995 97.343 0.6 1号测试集 8 1 030 77.476 0.4
Table 2. Complex gesture recognition results
View tableView in ArticleTable 2. Complex gesture recognition results
测试序列 种类 数量 正确率/% 时间/s 手势8 1 2 407 96.053 0.7 手势9 1 1 866 94.266 0.6 手势10 1 1 247 90.377 0.4 手势11 1 1 782 94.725 0.5 手势12 1 2 646 97.732 0.7 手势13 1 2 383 91.230 0.7
Get Citation
Copy Citation Text
Shang-en REN, Shu-jun XING, Shuo CHEN, Xun-bo YU, Bin-bin YAN, Kui-ru WANG, Xin-zhu SANG. Method for improving the accuracy of 3D light field interaction based on a small dataset of hand key points using an MLP network[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(9): 1198
Category: Research Articles
Received: Feb. 23, 2023
Accepted: --
Published Online: Sep. 19, 2023
The Author Email: Xin-zhu SANG (xzsang@bupt.edu.cn)
