As I commented, it is hard do give you a Answer which is fitting your Needs, because we don't know your needs. Still on Stackoverflow is a quite common solution for a problem like this.
To prevent Link corruption I add the Answer here too:
You can convert your Image into a YUV Image and then perform a histogram equalization on the Y channel. After that convert it back to RGB (if needed). With this method, you can normalize the luminance of your Image.
Code in opencv c++ would be:
cv::cvtColor(img, img, CV_BGR2YUV);
std::vector<cv::Mat> channels;
cv::split(img, channels);
cv::equalizeHist(channels[0], channels[0]);
cv::merge(channels, img);
cv::cvtColor(img, img, CV_YUV2BGR);
For more details look at the Link and note: this is not a solution I came up with it was the solution of Aurelius from stackoverflow
The Y-Component of a YUV Image holds the Luminance Information. Normalizing the Luminance would end in the effect, that you try to normalize the Light or Darkness in a Image the effect is shown in the Answer of Aurelius. I can't tell exactly how it differs from a regular equalization as you are mentioning it (As said, it is not actually my answer) If you want to know more, try to comment the Answer in stackoverflow so Aurelius could answer it.
Asked: 2016-12-05 01:22:48 -0600
Seen: 20,572 times
Last updated: Dec 05 '16
It is too "wide" question to get the simple answer. What kind of bad conditions did you mean?
your question is broad, we can't really suggest you sth. if we don't know more details.