Research Article
Deep-Learning-Based Approach for Iraqi and Malaysian Vehicle License Plate Recognition
Table 7
Detection results for Iraqi plates (YOLOV2).
| ā | Data volume | LP detection | LP recognition | Total training images | Total testing images | Training set | Testing set | Training | Testing | # of failures | # of wrongly detected | # of failures | # of wrongly detected | Detection rate | Detection rate |
| Fold 1 | 314 | 90 | 7 | 10 | 4 | 4 | 94.59 | 91.11 | Fold 2 | 332 | 72 | 0 | 20 | 8 | 1 | 93.98 | 87.50 | Fold 3 | 327 | 77 | 0 | 13 | 3 | 2 | 96.02 | 93.51 | Fold 4 | 329 | 75 | 0 | 15 | 5 | 1 | 95.44 | 92.00 | Fold 5 | 314 | 90 | 0 | 12 | 6 | 4 | 96.18 | 88.89 | Average | ā | 95.24 | 90.60 |
|
|