如何确定OpenCV中的像素是黑色还是白色？

Question

I have this code in Python:

width = cv.GetSize(img_otsu)[0]
height = cv.GetSize(img_otsu)[1]
#print width,":",height
for y in range(height):
    for x in range(width):
        if(img_otsu[y,x]==(255.0)):
            CountPixelW+=1
        if(img_otsu[y,x]==(0.0)):
            CountPixelB+=1

I want to convert this Python code to C++

This is what I have so far:

cv::threshold(img_gray,img_otsu,0.0,255.0,cv::THRESH_BINARY+cv::THRESH_OTSU);


for(int y =0;y<=img_otsu.size().height;y++)
    for(int x=0;x<=img_otsu.size().width;x++)
    {
        //Check Pixel 0 or 255 This is Problem
    }

How to I check if the pixel is black or white in C++?

Answer 1

You can use the at() function for Mat objects (see OpenCV docs ).

img_otsu.at<uchar>(y,x) will return the value of the element in the matrix at that position. Note that you may have to change uchar to whatever type of matrix img_otsu is (eg, float or double ). Once you get the value, simply compare it to 0 or 255.