（六）阀值

1.简单的阀值如上章所示，但是需要经验值确定阀值，很多情况不合适

2.采用一种自适应阀值处理图像

 import cv2                                                                                                                           
 import numpy as np
 
 img= cv2.imread('bookpage.jpg')
 
 grayscaled = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
 #自适应阀值
 gaus = cv2.adaptiveThreshold(grayscaled,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY,115,1)
 
 cv2.imshow('after',gaus)
 cv2.imshow('img',img)
 cv2.waitKey(0)
 cv2.destroyAllWindows()

3.另一种版本的门限是 Otsu's threshold，在这里效果并不好

retval2,otsu = cv2.threshold(grayscaled,125,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)