Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
jackyu e004f4e4e5 | 6 years ago | |
---|---|---|
Font | 7 years ago | |
Prj-Android/app | 6 years ago | |
Prj-Linux | 6 years ago | |
Prj-Win | 6 years ago | |
cache/finemapping | 7 years ago | |
dataset | 6 years ago | |
demo_images | 6 years ago | |
hyperlpr | 6 years ago | |
hyperlpr_py3 | 6 years ago | |
hyperlpr_test | 6 years ago | |
images_rec | 6 years ago | |
model | 6 years ago | |
templates | 7 years ago | |
HyperLprGUI.py | 6 years ago | |
LICENSE | 7 years ago | |
README.md | 6 years ago | |
batch.py | 7 years ago | |
benchmark.py | 7 years ago | |
config.json | 6 years ago | |
upload.py | 7 years ago | |
wxpy_uploader.py | 7 years ago |
This research aims at simply developping plate recognition project based on deep learning methods, with low complexity and high speed. This
project has been used by some commercial corporations. Free and open source, deploying by Zeusee.
HyperLPR是一个使用深度学习针对对中文车牌识别的实现,与较为流行的开源的EasyPR相比,它的检测速度和鲁棒性和多场景的适应性都要好于目前开源的EasyPR。
增加了端到端模型的cpp实现(Linux)(2018.1.31)
增加字符分割训练代码和字符分割介绍(2018.1.)
更新了Android实现,大幅提高准确率和速度 (骁龙835 (720x1280) ~50ms )(2017.12.27)
添加了IOS版本的实现(感谢xiaojun123456的工作)
添加端到端的序列识别模型识别率大幅度提升,使得无需分割字符即可识别,识别速度提高20% (2017.11.17)
新增的端到端模型可以识别新能源车牌、教练车牌、白色警用车牌、武警车牌 (2017.11.17)
更新Windows版本的Visual Studio 2015 工程(2017.11.15)
增加cpp版本,目前仅支持标准蓝牌(需要依赖OpenCV 3.3) (2017.10.28)
from hyperlpr import pipline as pp
import cv2
image = cv2.imread("filename")
image,res = pp.SimpleRecognizePlate(image)
print(res)
cd cpp_implementation
mkdir build
cd build
cmake ../
sudo make -j
车牌识别框架开发时使用的数据并不是很多,有意着可以为我们提供相关车牌数据。联系邮箱 455501914@qq.com。
如果您愿意支持我们持续对这个框架的开发,可以通过下面的链接来对我们捐赠。
高性能开源中文车牌识别框架
C++ Java C Python CMake other