MCPcopy
hub / github.com/we0091234/Chinese_license_plate_detection_recognition

github.com/we0091234/Chinese_license_plate_detection_recognition @main sqlite

repository ↗ · DeepWiki ↗
460 symbols 1,481 edges 45 files 31 documented · 7%
README

What's New

2026.02.13 yolo26车牌检测识别YOLO26-plate

2022.12.04 车辆和车牌一起检测看这里车辆系统

yolov8 车牌检测+识别

yolov7 车牌检测+识别

安卓NCNN

联系

模型用的是公开数据集训练出来的,需要准确率更高的模型,或者商务合作请加V

可代做学生毕设,以及课设大作业等

wechat: we0091234 (注明来意)

最全车牌识别算法,支持12种中文车牌类型

环境要求: python >=3.6 pytorch >=1.7

图片测试demo:

直接运行detect_plate.py 或者运行如下命令行:

python detect_plate.py --detect_model weights/plate_detect.pt  --rec_model weights/plate_rec_color.pth --image_path imgs --output result

测试文件夹imgs,结果保存再 result 文件夹中

视频测试demo 2.MP4 提取码:41aq

python detect_plate.py --detect_model weights/plate_detect.pt  --rec_model weights/plate_rec_color.pth --video 2.mp4

视频文件为2.mp4 保存为result.mp4

车牌检测训练

车牌检测训练链接如下:

车牌检测训练

车牌识别训练

车牌识别训练链接如下:

车牌识别训练

支持如下:

  • [X] 1.单行蓝牌
  • [X] 2.单行黄牌
  • [X] 3.新能源车牌
  • [X] 4.白色警用车牌
  • [X] 5.教练车牌
  • [X] 6.武警车牌
  • [X] 7.双层黄牌
  • [X] 8.双层白牌
  • [X] 9.使馆车牌
  • [X] 10.港澳粤Z牌
  • [X] 11.双层绿牌
  • [X] 12.民航车牌

Image

部署

1.安卓NCNN

2.onnx demo 百度网盘: k874

python onnx_infer.py --detect_model weights/plate_detect.onnx  --rec_model weights/plate_rec_color.onnx  --image_path imgs --output result_onnx

3.tensorrt 部署见tensorrt_plate

4.openvino demo 版本2022.2

 python openvino_infer.py --detect_model weights/plate_detect.onnx --rec_model weights/plate_rec.onnx --image_path imgs --output result_openvino

References

More

qq群:769809695(三群新开) 871797331(已满) 837982567(二群已满) 询问

Core symbols most depended-on inside this repo

tolist
called by 25
models/common.py
info
called by 22
models/yolo.py
plot
called by 15
utils/metrics.py
log
called by 14
utils/wandb_logging/wandb_utils.py
time_synchronized
called by 11
utils/torch_utils.py
xyxy2xywh
called by 10
utils/general.py
letterbox
called by 10
utils/datasets.py
xywh2xyxy
called by 9
utils/general.py

Shape

Function 235
Method 167
Class 58

Languages

Python100%

Modules by API surface

models/common.py66 symbols
utils/datasets.py49 symbols
utils/general.py32 symbols
utils/face_datasets.py31 symbols
utils/torch_utils.py21 symbols
utils/wandb_logging/wandb_utils.py19 symbols
utils/activations.py19 symbols
openvino_infer.py19 symbols
models/experimental.py19 symbols
utils/plots.py18 symbols
utils/loss.py18 symbols
onnx_infer.py16 symbols

For agents

$ claude mcp add Chinese_license_plate_detection_recognition \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact