I am doing Near Infrared image face detection (video based). But I want to save the detected image with a good quality only; here I think I will focus on sharpness and illumination of the detected face. Any idea on how to this with OpenCV?
This work for me in C++. The one that I learnt from http://answers.opencv.org/question/5395
double contrast_measure(const Mat&img)
{
Mat dx, dy;
Sobel(img, dx, CV_32F, 1, 0, 3);
Sobel(img, dy, CV_32F, 0, 1, 3);
magnitude(dx, dy, dx);
return sum(dx)[0];
}
int main(int argc, const char** argv)
{
//my coding
std::cout << "contrast=" << contrast_measure(face) / 1e3 << std::endl; //face is my image name
//my coding
}Asked: Oct 28 '15
Seen: 636 times
Last updated: Oct 29 '15
take a look at http://answers.opencv.org/question/5395 to measure sharpness of the image.
Be carefull to use the C++ API, C-API is deprecated and may not work