OpenCV自适应二值化

《OpenCV系列教程》
项目位置：OpenCV-Sample
代码位置：18-AdaptThresholding.py

import cv2 as cv
from matplotlib import pyplot as plt

img = cv.imread('./res/CarID.jpeg',0)

ret,thresh1 = cv.threshold(img,120,255,cv.THRESH_BINARY)
ret,thresh2 = cv.threshold(img,120,255,cv.THRESH_BINARY_INV)
ret,thresh3 = cv.threshold(img,120,255,cv.THRESH_TRUNC)
ret,thresh4 = cv.threshold(img,120,255,cv.THRESH_TOZERO)
ret,thresh5 = cv.threshold(img,120,255,cv.THRESH_TOZERO_INV)
titles = ['Original Image','BINARY','BINARY_INV','TRUNC','TOZERO','TOZERO_INV']
images = [img, thresh1, thresh2, thresh3, thresh4, thresh5]
for i in range(6):
    plt.subplot(2,3,i+1),plt.imshow(images[i],'gray')
    plt.title(titles[i])
    plt.xticks([]),plt.yticks([])
plt.show()

使用自适应二级化，让编程更加方便。

• cv.ADAPTIVE_THRESH_MEAN_C 取自相邻区域的平均值。
• cv.ADAPTIVE_THRESH_GAUSSIAN_C 取相邻区域的加权和，权重为一个高斯窗口。