车牌识别学习记录

cv2.imdecode(np.fromfile(filename, dtype=np.uint8), cv2.IMREAD_COLOR)
讲解：
1. np.fromfile() 读取图片，返回height,width,channels
2. [cv2.imdecode](http://www.voidcn.com/article/p-sabqihis-bry.html)
cv2.imdecode()函数:
从指定的内存缓存中读取数据，并把数据转换(解码)成图像格式;主要用于从网络传输数据中恢复出图像。
cv2.imencode()函数:
将图片格式转换(编码)成流数据，赋值到内存缓存中;主要用于图像数据格式的压缩，方便网络传输。

2. img = cv2.filter2D()

#https://www.cnblogs.com/lfri/p/10599420.html
img = cv2.filter2D

3.cv2.GaussianBlur

https://www.jianshu.com/p/bfd5dd2566bb

4.cv2.morphologyEx

https://www.jianshu.com/p/dcecaf62da71

5. cv2.threshold

https://blog.csdn.net/a19990412/article/details/81172426
https://blog.csdn.net/on2way/article/details/46812121

6. cv2.Canny

https://blog.csdn.net/weixin_30390075/article/details/99054386
https://blog.csdn.net/wsp_1138886114/article/details/82935839

7.cv2.findContours

https://blog.csdn.net/hjxu2016/article/details/77833336

8. cv2.minAreaRect

# https://blog.csdn.net/lanyuelvyun/article/details/76614872
# https://blog.csdn.net/qq_37385726/article/details/82313558

9. cv2.boxPoints

https://blog.csdn.net/claroja/article/details/83114131
https://www.cnblogs.com/Undo-self-blog/p/8438808.html

10.cv2.getAffineTransform

https://segmentfault.com/a/1190000015645951

11. cv2.rectangle

确实是靠 确定对角线 来画矩形的。
cv2.rectangle(img, (bbox.left, bbox.top), (bbox.right, bbox.bottom), (0,0,255), 2)
0,255,0）：画线对应的rgb颜色
　　　2：所画的线的宽度
import cv2
cv2.rectangle(img, (x1, y1), (x2, y2), (255,0,0), 2)

x1,y1 ------
|          |
|          |
|          |
--------x2,y2

来源：oschina

链接：https://my.oschina.net/112612/blog/3213122