Table 1 Speckle-based DNN comparison. Our method reaches an accuracy of 95% while maintaining a high recall of 98% in active-sense classification task. In an active-sense classification task, the full video approach achieved 89% accuracy and 93% precision. Our model takes 2 ms per batch to infer, while the single-frame method takes 4 ms, and the full-video method takes 830 ms.
From: Remote photonic detection of human senses using secondary speckle patterns
Model | Classes | Accuracy (%) | Precision (%) | Recall (%) | F1 (%) | Inference time (ms) |
|---|---|---|---|---|---|---|
Single speckle frame convnet | Sense | 82 | 85 | 78 | 82 | 4 |
No Sense | 79 | 83 | 4 | |||
Full video speckle convnet | Sense | 89 | 93 | 91 | 89 | 830 |
No Sense | 84 | 87 | 830 | |||
Our model | Sense | 95 | 98 | 92 | 95 | 2 |
No Sense | 92 | 98 | 2 |
