Practical overview
When it fits
Use it when a Python-based workflow for Chinese license-plate detection and character recognition in images or video matches your task, or when you need a starting point for the linked training and deployment paths.
Who it is for
- Developers building image or video workflows to detect and read Chinese vehicle plates.
- Practitioners exploring plate-detector or character-recognition training.
- Teams adapting plate inference to ONNX, OpenVINO, TensorRT, or an Android NCNN implementation.
Documented uses
- Process an image folder and save plate-recognition results.
- Analyze a video and produce a result video.
- Train or fine-tune the detector or recognition model using the linked resources.
- Use documented ONNX or OpenVINO inference paths, or explore separately linked TensorRT and Android NCNN implementations.
Requirements & limits
- The README requires Python 3.6 or later and PyTorch 1.7 or later for the main demos.
- The listed plate coverage includes single-row and double-row formats and several Chinese plate categories.
- Detector training and recognition training are linked to separate resources.
- The ONNX and OpenVINO examples require model files; the README labels the OpenVINO demo as version 2022.2.
- TensorRT and Android NCNN are presented through separate linked projects rather than as commands within the main repository.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Run the documented image-folder inference example
Process images in a folder and save the plate-recognition results to an output folder.
Before you start
- Python 3.6 or later and PyTorch 1.7 or later.
- The repository’s detector and recognizer weight files.
- A folder of input images.
Steps
Place the images in the input folder, such as
imgs.Run the command below.
python detect_plate.py --detect_model weights/plate_detect.pt --rec_model weights/plate_rec_color.pth --image_path imgs --output result
Expected outcome
The example specifies `result` as the folder for image results.
Guide limitations
- The command is an instruction from the project documentation, not a verified execution result.
Run the documented OpenVINO image-folder demo
Use the repository’s OpenVINO demo to process an image folder with ONNX model files.
Before you start
- OpenVINO version 2022.2, as specified in the README.
- ONNX detector and recognizer model files.
- A folder of input images.
Steps
Place the images in the input folder, such as
imgs.Run the command below.
python openvino_infer.py --detect_model weights/plate_detect.onnx --rec_model weights/plate_rec.onnx --image_path imgs --output result_openvino
Expected outcome
The example specifies `result_openvino` as the output folder.
Guide limitations
- The README documents an image-folder demo, not an OpenVINO video workflow.
- The command is documented guidance, not a verified execution result.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 14 October 2026
- Original website title
- we0091234/Chinese_license_plate_detection_recognition · Official homepage title · retained in its source language