Research Article
Tamil OCR Conversion from Digital Writing Pad Recognition Accuracy Improves through Modified Deep Learning Architectures
Table 3
Evaluation of classifier performance through statistical measures.
| References | Classifiers | Accuracy | Precision (%) | Recall (%) | F1 score (%) |
| [21] | CNN + SALA | 86.3% | 88.4 | 94.3 | 91.2 | [22] | AlexNet | 90.5% | 92.6 | 98.5 | 95.4 | [22] | VGG19Net | 92.5% | 93.5 | 96.7 | 95.0 | [23] | MMU-SNet | 96.8% | 99.3 | 97.4 | 98.3 | Proposed | RTSBA | 98.7% | 99.3 | 99.2 | 99.3 |
|
|
MMU-SNet, modified multi-scale segmentation network.
|