What's new
Photoshop Gurus Forum

Welcome to Photoshop Gurus forum. Register a free account today to become a member! It's completely free. Once signed in, you'll enjoy an ad-free experience and be able to participate on this site by adding your own topics and posts, as well as connect with other members through your own private inbox!

Colouring Black & White photo


The algorithm seems to do a pretty good job.

I'm very curious..........when you stated, "I've searched but didn't find any info here about this". Did you mean for algorithms or information/tutorials on how to colorize black and white photos?
 
@revnart - Thanks for finding that algorithm together with an easy on-line interface to it.

The quality of its results surprised me compared to what I was expecting (which wasn't very much, LOL).

I have not submitted any of my own images to it. However, if I did want to test it, I think I would start with a best-case scenario: I would desaturate an existing, high quality color image, submit the B&W version, and see how close the algorithm would come to the original color version.

BTW, the links Sam provided, particularly, the last 3, discuss methodology. As I said in some of those posts from a few years ago, I still use gradient maps when I have to this sort of work, although, to be honest, it's definitely not my favorite way to spend time, LOL.
@IamSam - Thanks for looking up those threads. I was going to do it myself when your post appeared. :thumbsup:

Cheers,

Tom M
 
Last edited:
I would desaturate an existing, high quality color image, submit the B&W version, and see how close the algorithm would come to the original color version.

Tom,
Sorry, I'm not following this comment at all. Below are three completely different colors, which, when desaturated, result in precisely identical gray tones. How could any software (or human) possibly determine the original color simply by examining a gray tone? If we were colorizing a person's shirt from the gray tone below, it's completely arbitrary which Hue to select and there is no such thing as 'correct' or 'accurate'. Am I missing something?

Rich

Colors.jpg
 
You hit the nail on the head, Rich. What you pointed out is exactly correct: there are many different combinations of hue and saturation that can lead to the same gray value (... or luminance value, or brightness value, etc.).

The only way that this or any other algorithm has a chance of assigning colors correctly is if it is smart enough to classify various areas in an image based on factors such as their shape, size, texture, boundary shape & complexity, etc. If it can pull that off (which it apparently can, with some accuracy), then, for example, it won't often assign a dull green to the bottom of a storm cloud, or a light Caucasian skin tone to a moderately bright area in a sunset photo, even though they both may have the same gray value.

If their many-layered (i.e., "deep learning") neural net algorithm is smart enough (and has enough exemplars to train on), then theoretically, it might eventually even be able to distinguish between similar areas (eg, a evergreen vs a deciduous forest) and color them appropriately.

After all, this is almost exactly how we manually colorize B&W photos: If we are observant and have a good artistic sense, we will likely have a good idea what colors to use in many areas of the image, and take our best guess at the areas we know nothing about (eg, clothing that could be almost any color, but the same luminance value).

So, my idea was to generate very difficult test cases for their algorithm that would indirectly tax / test its feature recognition abilities.

HTH,

Tom M

PS - @Rich54 - I just re-read my post and realized that my use of the term, "best case scenario" may have been confusing. This was only meant to imply that if their algorithm couldn't do well with perfectly exposed, well focused, well lit, moderate contrast photos, then it would surely do much worse with average quality photos. It wasn't meant to imply that I thought that the results would actually be good -- just that they would show off the best that the algorithm could possibly achieve.
 
Last edited:

Back
Top