《OpenCV系列教程》
项目位置:OpenCV-Sample
代码位置:17-ImageThresholding.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()
运行效果:
threshold(src, thresh, maxval, type, dst=None) 参数介绍:
- src原图片。
- 阈值
- 图像中最大值
- enum cv::ThresholdTypes
Enumerator | |
---|---|
THRESH_BINARY Python: cv.THRESH_BINARY | ???(x,y)={??????0if ???(x,y)>??????otherwise |
THRESH_BINARY_INV Python: cv.THRESH_BINARY_INV | ???(x,y)={0??????if ???(x,y)>??????otherwise |
THRESH_TRUNC Python: cv.THRESH_TRUNC | ???(x,y)={????????????(x,y)if ???(x,y)>??????otherwise |
THRESH_TOZERO Python: cv.THRESH_TOZERO | ???(x,y)={???(x,y)0if ???(x,y)>??????otherwise |
THRESH_TOZERO_INV Python: cv.THRESH_TOZERO_INV | ???(x,y)={0???(x,y)if ???(x,y)>??????otherwise |
THRESH_MASK Python: cv.THRESH_MASK | |
THRESH_OTSU Python: cv.THRESH_OTSU | flag, use Otsu algorithm to choose the optimal threshold value |
THRESH_TRIANGLE Python: cv.THRESH_TRIANGLE | flag, use Triangle algorithm to choose the optimal threshold value |
看着有些复杂,通过一个更直观的变换看一看吧:
第一张是原始图片,原始图片为一张渐变图片最右边为纯白,最左边为纯黑,闸值选的为‘127’ ,在做BINARY变换时,大于127的值全部变成黑色,小于127的值全部变白。
BINARY_INV变换,正好相反,大于127的变白,大于127的变黑。省下的三个变换,应该看看就能懂是啥意思了吧?