Take the 2-minute tour ×
Super User is a question and answer site for computer enthusiasts and power users. It's 100% free, no registration required.

I have a set of photos X taken with camera 1 and a set of photos Y taken with camera 2 of the same objects. I want to find a transformation such that when I apply it to a photo Xi, the output will be the same as photo Yi (for a given object i).

I did not take the photos, but I'm assuming the photos in X were taken with bad or artificial lighting, whereas the photos in Y have good natural light.

I want to eventually make a browser extension by which I can right click on an image and select "apply color transformation" for this specific transformation. But to start, just figuring out how to do it in GIMP or Photoshop would be great.

Here's an example of the bad color followed by the good color. I have many elements in X and Y of varying colors in order to tune the transformation.

bad color

good color

share|improve this question
    
Its made more complex by the fact that one image is a closeup while one is shot from a distance, as well as the fact that the quality of the images is completely different. I will be interested to see if someone can come up with a solution. I couldn't seem to find any other way than using hue/saturation in Photoshop. –  Sam Jan 31 '12 at 8:11
    
While I think you are overoptimistic, what you are describing is essentially white point conversion/chromatic adaption –  horatio Jan 31 '12 at 16:53
    
In addition, the bottom photo (presuming the whites are white) is underexposed, and the top one is overexposed. The underexposed one can be brought up, but the top one has lost all detail in the whites. –  horatio Jan 31 '12 at 16:55

1 Answer 1

I can suggest you this script, it will adjust colours to match in average:

https://gist.github.com/1711451

Don't expect it to do magic if your images are not exactly similar or if some of them are badly exposed.

Your “bad” image modified (average colours and intensity match “good” image almost exactly). Please note, that it doesn't make them “correct”, it just matches the overall image tint. Another approach might be to match only white colours...

bad image modified

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.