My project consist of classification of images using ML. The images are microscopic slices. For the feature extraction phase, I am using multiple filters and got a good result.
So I decided to do a preprocessing for the images with the objective to standardize them before feature extraction and it came to me do a hiistogram equalization Because I am not using this as features, I would like to know how to quantify the improvement of the quality of images.
I've used before a sharpness quantification, DOM if I am not wrong