Research Article
Deep-Learning-Based Approach for Iraqi and Malaysian Vehicle License Plate Recognition
Table 6
Detection results for Malaysian 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 | 540 | 141 | 8 | 10 | 3 | 11 | 96.67 | 90.07 | Fold 2 | 555 | 126 | 7 | 42 | 5 | 14 | 91.17 | 84.92 | Fold 3 | 549 | 132 | 9 | 11 | 6 | 3 | 96.36 | 93.18 | Fold 4 | 544 | 137 | 20 | 10 | 10 | 2 | 94.49 | 91.24 | Fold 5 | 536 | 145 | 5 | 6 | 3 | 9 | 97.95 | 91.72 | Average | ā | 95.33 | 90.23 |
|
|