Suppose having two images on a given scale, for example it could be the classic [0-255], representing the same thing but with different value intensities, i.e. the first could have a maximum pixel value of 125 across the image and the second of 200. Could an intensity normalization with respect to their maximum value (and not on the maximum value allowed from the scale) be helpful for something for deep-learning purposes? Or it's enough the classical preprocessing with dataset mean-centering and standardization as in Why normalize images by subtracting dataset's image mean, instead of the current image mean in deep learning? ?

In particular I was wonderng if a normalization of this type could help in this case I found on stackoverflow: https://stackoverflow.com/questions/60406759/how-to-standardize-image-data-for-a-simple-unet . Thank you.


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.