Research Article
Deep-Learning-Based Approach for Iraqi and Malaysian Vehicle License Plate Recognition
Table 13
Recognition results for Iraqi plates (YOLOV2).
| ā | Data volume | LP detection | LP recognition | # training images | # testing images | Training set | Testing set | Training | Testing | # of failures | # of wrongly detected | # of failures | # of wrongly detected | Recognition rate | Recognition rate |
| Fold 1 | 307 | 82 | 4 | 14 | 0 | 13 | 94.14 | 84.15 | Fold 2 | 292 | 64 | 0 | 12 | 0 | 9 | 95.89 | 85.94 | Fold 3 | 303 | 74 | 2 | 12 | 3 | 11 | 95.38 | 81.08 | Fold 4 | 301 | 74 | 2 | 13 | 3 | 9 | 95.02 | 83.78 | Fold 5 | 295 | 84 | 0 | 2 | 0 | 6 | 99.32 | 92.86 | Average | ā | 95.95 | 85.56 |
|
|