TPThelen you are right, there is no such filter right now. I would like to understand better your use case, if you don’t mind. Do you intend to mark up every single photo in your archive?

It is just that from my experience as the owner of 1Tb of photo archive, I don’t really see myself trying to markup every single photo there, its just not really feasible.

It is a chore but would be simplified if I knew which ones still need attention. Could skip over the confirms but the unknowns (Red) would help to ensure they get to the right person’s folder.

You see, the thing is that there are multiple reasons why recognition may not work properly. Face could be too uncertain due to low lighting of the photo, or too low resolution, or person might be looking away, or that might be not a face at all, but incorrectly identified as face (face of a statue or face on a painting, for example). Also, face can be considered as recognised, but it can be assigned to wrong person. Or there could even be no face detected on the photo, while there is.

My point is, if AI would have means to detect its own mistakes, it would not do those mistakes in the first place. So it cannot really help in detecting where it went wrong, or what it has missed, unfortunately.

If the goal is to have 100% faces marked up, I guess the only reasonable way is just doing a full review of all photos. Not that I would suggest doing that, but if that’s the goal, then first you need to decide the order in which you would go thru all of your collection. Will it be folder by folder or event by event on the time line. Or, maybe there is just limited set of folders or events - that would simplify the task.

Then I would suggest going to the first photo of next folder/event, open it then, open File Info panel and then just click next, next, next. File info panel will give immediate view on all identified people on the image, as well as detected, but unassigned faces. Also, you could quickly see if the number of faces matches number of people on the photo (if that is not a group photo). And take immediate action in case of mistakes.

For a group photos you can’t immediately tell if everything is OK just by looking to the File Info panel. Here you can use another trick - hover your mouse over ever single face on the image and check if all of them were identified, if they were tagged properly. This way you could do it quite efficiently.

However, my recommendation would be making pauses in that process once you made significant amount of manual changes, switching back to People mode, and see what AI has to suggest, based on the new information you have given it to learn on. Since this process is 1000 times more efficient, you don’t wont to go back to manual review again until AI is already done with its suggestions for now.

Hope that helps.

I follow this and already understood most of it. I’ve used similar software in the past. It is just that it is easy for pictures to sneak into a folder (Especially when starting out or having multiple backups that have identical folders and but not all the same pictures). Also, in the People folder, when you Identify the person in the folder the picture drops to the bottom of the set for that person. Being able to identify pictures w unidentified faces would help immensely.

TPThelen can you please tell how you think that feature wold work? I mean from user perspective.

TPThelen Also, in the People folder, when you Identify the person in the folder the picture drops to the bottom of the set for that person

That behaviour got a lot of criticism lately, so I am changing it in the next release.

TPThelen I would set a radio button in the top margin to turn the feature on/off so it is readily apparent that the setting is on.

I could think of a couple ways to show which pictures need attention:
Ability to hide pictures that do not have questionable faces. This could potentially show only ones with red questionable ones or all questionable ones. This would be the preferred as it would give you exactly what you are looking for if you are looking to validate faces.
Display number of red and number of yellow questionable faces next to the pictures. This would be less desirable as you would have to scroll thru the entire file to find them.

Am I right that here you are speaking about Folders view?

Yes.

The new feature to select and confirm (Or not confirm) multiple photos in people view was a huge improvement in efficiency! Still like to be able to identify all pictures in a folder w unconfirmed faces. I still run across photos with faces that have not been linked to people in my list (Especially family group photos) and showing the icons of those pictures would help me select the ones I want to investigate further. Thanks!

Hi! About Unassigned Faces view. Why, I think, it will be very useful for some of users. Now I have 1000 photos of kids from school, there is some faces looking straight up to camera, and they are recognized perfectly, but some of them looking down (but in aestethic way), and they goes to unassigned. I can help the program to identify them very quickly If they will be in a View of all unassigned. But now I dont know, are they identified, or not, how much are they and so on.

Andrejs Thank you. I am getting more and more request like that recently, so I am already thinking what would be the best approach to solve this problem.

I would like to add my voice to show my support for an identified photo selector grouped by identical faces. This would probably assist greatly in more identifications.

JusIt should be in person view (Similar to Picassa)

This is an important feature for anyone who is trying to build up a bunch of new identities in thousands of images. If you tag one or two faces sometimes it doesn’t find more, and manually searching all images to find more is a real pain. I just bought this for my ML training, and this is one of the biggest missing features.

Great addition.
Thanlk you