Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Jackyu b63bdf142c | 7 years ago | |
---|---|---|
Font | 7 years ago | |
cache/finemapping | 7 years ago | |
dataset | 7 years ago | |
demo_images | 7 years ago | |
hyperlpr | 7 years ago | |
hyperlpr_test | 7 years ago | |
model | 7 years ago | |
templates | 7 years ago | |
.gitignore | 7 years ago | |
0.jpg | 7 years ago | |
0_rough.jpg | 7 years ago | |
LICENSE | 7 years ago | |
README.md | 7 years ago | |
batch.py | 7 years ago | |
benchmark.py | 7 years ago | |
config.json | 7 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是一个基于Python的使用深度学习针对对中文车牌识别的实现,与开源的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EasyPR。
step1. 使用opencv 的 HAAR Cascade 检测车牌大致位置
step2. Extend 检测到的大致位置的矩形区域
step3. 使用类似于MSER的方式的 多级二值化 + RANSAC 拟合车牌的上下边界
step4. 使用CNN Regression回归车牌左右边界
step5. 使用基于纹理场的算法进行车牌校正倾斜
step6. 使用CNN滑动窗切割字符
step7. 使用CNN识别字符
from hyperlpr import pipline as pp
import cv2
image = cv2.imread("filename")
image,res = pp.SimpleRecognizePlate(image)
hyperlpr_test文件夹下
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。
高性能开源中文车牌识别框架
C++ Java C Python CMake other