Research Article
MyoTac: Real-Time Recognition of Tactical Sign Language Based on Lightweight Deep Neural Network
Table 3
Comparison results of 3 models.
| | Model | Accuracy (MyoDataSet) | Accuracy () | Accuracy (our dataset) | Model size | Processing time (our dataset) |
| | EMGNet | 94.3% | 82% | 13.1% | 744 k | — | | MyoSign | — | — | 91.3% | 17.0 M | 18 ms | | MyoTac | 98.1% | 85% | 92.4% | 3.7 M | 2.37 ms |
|
|
