https://github.com/pandede/wpodnet-pytorch
The implementation of ECCV 2018 paper "License Plate Detection and Recognition in Unconstrained Scenarios" in PyTorch
https://github.com/pandede/wpodnet-pytorch
ai computer-vision deep-learning license-plate-recognition object-detection python torch wpod wpod-net
Last synced: about 3 hours ago
JSON representation
The implementation of ECCV 2018 paper "License Plate Detection and Recognition in Unconstrained Scenarios" in PyTorch
- Host: GitHub
- URL: https://github.com/pandede/wpodnet-pytorch
- Owner: Pandede
- License: gpl-3.0
- Created: 2022-03-29T14:44:36.000Z (about 3 years ago)
- Default Branch: master
- Last Pushed: 2025-01-04T07:35:37.000Z (4 months ago)
- Last Synced: 2025-04-28T11:15:52.471Z (about 3 hours ago)
- Topics: ai, computer-vision, deep-learning, license-plate-recognition, object-detection, python, torch, wpod, wpod-net
- Language: Python
- Homepage:
- Size: 1.65 MB
- Stars: 22
- Watchers: 1
- Forks: 8
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# WPODNet: Build with Torch
## Introduction
This repository implements the proposed method from **ECCV 2018 paper ["License Plate Detection and Recognition in Unconstrained Scenarios"](https://openaccess.thecvf.com/content_ECCV_2018/papers/Sergio_Silva_License_Plate_Detection_ECCV_2018_paper.pdf)** in Torch.
The model in Keras is built by the essay author, see [sergiomsilva/alpr-unconstrained](https://github.com/sergiomsilva/alpr-unconstrained).
Example
Annotated
Warp perspective
Confidence
0.9841
0.9945
0.9979
## Quick Run
1. Clone this repository
```bash
git clone https://github.com/Pandede/WPODNet-Pytorch.git
```
2. Install [PyTorch](https://pytorch.org) depends on your environment.
3. Install packages in `requirements.txt`
```bash
pip3 install -r requirements.txt
```
4. Download the pretrained weight `wpodnet.pth` from [here](https://github.com/Pandede/WPODNet-Pytorch/releases/download/1.0.0/wpodnet.pth)
5. Predict with an image
```bash
python3 predict.py docs/sample/original/03009.jpg # The path to the an image
# docs/sample/original # OR the path to the directory with bulk of images
-w weights/wpodnet.pth # The path to the weight
--save-annotated docs/sample/annotated # The directory to save the annotated images
--save-warped docs/sample/warped # The directory to save the warped images
```
## Future works
- [x] Inference with GPU
- [x] Inference with bulk of images
- [ ] Inference with video
- [ ] Introduce training procedure
- [x] The matrix multiplication seems weird in function `postprocess`, may improve the computation.
## Citation
```bibtex
@inproceedings{silva2018license,
title={License plate detection and recognition in unconstrained scenarios},
author={Silva, Sergio Montazzolli and Jung, Cl{\'a}udio Rosito},
booktitle={Proceedings of the European conference on computer vision (ECCV)},
pages={580--596},
year={2018}
}
```