I want to learn computer vision and so I downloaded image processing slides from my university archive. I'm on histogram equalization. Learning about local histogram equalization points me out to this procedure:

The procedure is to define a square or rectangular window (m*n, n,m odds) and move the center of the window from pixel to pixel. At each location, the histogram of the points inside the window is computed and a histogram equalization transformation function is obtained. This function is finally used to map the intensity level of the pixel centered in the window to create a corresponding (processed) pixel in the output image. The center of the neighborhood region is then moved to an adjacent pixel location and the procedure is repeated.

(It is from a slide of my image processing course at university I don't think I can publish the link because it requires university credential)

I was wondering what kind of practical image this procedure can enhance. I have tried with this example image but it does nothing then increment noise signal (global histogram equalization is much better) and it is super slow (no real-time usage can be even thought).

Can you advice me some test image in which this equalization procedure can be effective? When can I use it for real enhancement? What kind of image? With low contrast and big dark zone? In general, when does a local equalization is better then global equalization? Is it really usefull?

In particular I'm interested in when local histogram equalization increment noise signal or when it doesn't.

And what about this particular procedure? I know that there are more specific tecniques (like Contrast limited adaptive histogram equalization). Is this a good tecnique?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.