 |
 |
 |
Check out the demo app on Hugging Face Spaces.
 |
① Registered Region ② Classification Number ③ Kana Character ④ 4-Digit Designation Number |
| License Plate Type | Engine Displacement | Marking Color | Background Color |
|---|---|---|---|
| Private Vehicles | ≥ 660 cc | Green | White |
| Private Vehicles | < 660 cc | Black | Yellow |
| Commercial Vehicles | ≥ 660 cc | White | Green |
| Commercial Vehicles | < 660 cc | Yellow | Black |
| Commemorative Plates | – | Green | Multiple |
- CNN adapted from Chinese License Plate Recognition System Based on Convolutional Neural Network
- Apple M1 with MPS hardware acceleration
- Number of epochs: 100
- Optimizer: Adam
- Initial learning rate: 1e-3
- Learning rate scheduler: StepLR, reduce by factor of 0.1 every 30 epochs
- Loss function: CrossEntropyLoss
- Random seed: 42
| Layer Depths | Samples | Classes | Accuracy | F1 Score | Params (×103) | |
|---|---|---|---|---|---|---|
| ① Region Name | 64, 128, 256, 512 | 412 | 134 | 0.976 | 0.973 | 1690 |
| ② Classification Number | 64, 128, 256 | 444 | 11 | 0.984 | 0.984 | 440 |
| ③ Kana Character | 64, 128, 256, 512 | 430 | 43 | 0.979 | 0.978 | 680 |
| ④ Designation Number | 64, 128, 256, 512 | 547 | 11 | 0.998 | 0.998 | 646 |
alpr_jp
Big thanks to dyama san for sharing the alpr_jp dataset.
https://github.com/dyama/alpr_jp
Chinese License Plate Recognition System Based on Convolutional Neural Network
H. Chen, Y. Lin, and T. Zhao, 'Chinese License Plate Recognition System Based on Convolutional Neural Network', Highlights in Science, Engineering and Technology, vol. 34, pp. 95–102, 2023.
https://www.researchgate.net/publication/369470024
License Plates Dataset
https://universe.roboflow.com/samrat-sahoo/license-plates-f8vsn
YOLOv8
https://github.com/ultralytics/ultralytics
ナンバープレートの見方 (How to Read a Number Plate)
https://wwwtb.mlit.go.jp/tohoku/jg/jg-sub29_1.html
This repository was created on Leap Day 2024.