参考博文:https://blog.csdn.net/u012771236/article/details/44975831
size:图像总像素个数
u:图像的平均灰度
w0:前景像素点占整幅图像大小的比例
u0:前景像素点的平均值
w1:背景像素点占整幅图像大小的比例
u0:背景像素点的平均值
g:类间方差
u = w0 * u0 + w1 * u1 (1)
g = w0*(u - u0)^2 + w1*(u - u1)^2 (2)
将(1)代入(2)得:
g = w0 * w1 * (u0 - u1)^2
import numpy as np
import cv2
import matplotlib.pyplot as plt # plt 用于显示图片
def OTSU_enhance(img_gray, th_begin=0, th_end=256, th_step=1):
assert img_gray.ndim == 2, "must input a gary_img"
max_g = 0
suitable_th = 0
for threshold in range(th_begin, th_end, th_step):
bin_img = img_gray > threshold
print(bin_img)
bin_img_inv = img_gray <= threshold
fore_pix = np.sum(bin_img)
back_pix = np.sum(bin_img_inv)
if 0 == fore_pix:
break
if 0 == back_pix:
continue
w0 = float(fore_pix) / img_gray.size
print(img_gray*bin_img)
u0 = float(np.sum(img_gray * bin_img)) / fore_pix
w1 = float(back_pix) / img_gray.size
u1 = float(np.sum(img_gray * bin_img_inv)) / back_pix
# intra-class variance
g = w0 * w1 * (u0 - u1) * (u0 - u1)
if g > max_g:
max_g = g
suitable_th = threshold
return suitable_th
img1 = cv2.imread('2.jpg')
img = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
print(OTSU_enhance(img))
ret, binary = cv2.threshold(img, 120, 255, cv2.THRESH_BINARY)
cv2.namedWindow('a', 0)
cv2.resizeWindow('a', 640, 480)
cv2.imshow('a', binary)
cv2.waitKey(0)
注意 bin_img 是布尔类型。