• Global community
    • Language:
      • Deutsch
      • English
      • Español
      • Français
      • Português
  • 日本語コミュニティ
    Dedicated community for Japanese speakers
  • 한국 커뮤니티
    Dedicated community for Korean speakers
Exit
0

Photoshop Element Organizer label grayed out people recognition

New Here ,
Apr 22, 2017 Apr 22, 2017

Copy link to clipboard

Copied

In Photoshop Element Organizer v15 I launched the recognition of faces.

Overall it works well.

But some labels appear grayed out unless I understand why.

Several cases:

-In 'All people' the face is displayed and the name is written below.

Yet when I click on the label, in the section "Faces confirmed", some labels are grayed out.

This is surprising since these face are confirmed (recognized)

and that by landing on a gray label the corresponding photo (with the right face).

-In 'All people' label is gray with the name written below.

When I click on the gray label, all labels "Faces confirmed" are grayed out.

And when I ask myself on a gray label, the corresponding photo appears (with the right face).

= What is the problem?

- And how to fix it so that all the labels display correctly?

Thanks for your help

Alain

Views

1.6K

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Adobe Employee ,
Apr 22, 2017 Apr 22, 2017

Copy link to clipboard

Copied

Can you please attach a screenshot highlighting the issue?

Are you working in Named view or Unnamed view?

Thanks,

Anwesha

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
New Here ,
Apr 23, 2017 Apr 23, 2017

Copy link to clipboard

Copied

Below, screenshot highlighting the issue.

I'm working in Named View

Copie écran.jpg

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Dec 29, 2019 Dec 29, 2019

Copy link to clipboard

Copied

I'm currently facing the same issue with Adobe Photoshop Elements Organizer 2020, also in Named View. In another thread, it broken down to having used face recognition in an earlier version of the software, which is not the case for me. (2020 is the first version I bought and I haven't used any other software on the all the pictures currently in the catalog before.)

 

So, are there any updates on this issue?

 

Thank you very much in advance,

Ben

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Expert ,
Dec 29, 2019 Dec 29, 2019

Copy link to clipboard

Copied

Ben, please describe everything you have done to name faces.

How many photos in your catalog?

Has face recognition completed?  The status of face recognition should show in the lower right corner of the status bar in the Media grid.

Have you named any faces by dragging a name to the image in the Media grid, rather than naming faces in the People tab?

Please give us a screenshot of what you are seeing.

And just to be clear about no other software touching the files, do any of the images come from a phone?

Finally, what OS are you using?

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Dec 29, 2019 Dec 29, 2019

Copy link to clipboard

Copied

Greg, thanks for your prompt reply. Here are my answers:

Only very few pictures at the moment, < 4k photos.

According to your description, face recognition should be finished as in the right part of the status bar, only the catalog name is displayed (see screenshot below).

Yes, I named people in the Media grid (which appears to me to be a possible way intended by the programmers), but by dragging the photo to the name (not vice versa as you described). The reason is that many pictures did not show up in the people tab. So is there any better way to tag people if the respective photos do not show up in the people tab?

All of the pictures currently in the tab came from two different Samsung (S10 / S10e) phones.

OS: Win 10 1909.

image.pngimage.png

 

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Expert ,
Dec 29, 2019 Dec 29, 2019

Copy link to clipboard

Copied

Yes, I named people in the Media grid (which appears to me to be a possible way intended by the programmers), but by dragging the photo to the name (not vice versa as you described).

 

This is the reason why you have generic icons for the faces.  By dragging a photo to a name in the People tag hierarchy, you are not associating the photo with a face.  This is true, whether face recognition has been completed or not. 

 

To determine whether FR has been completed, go to a photo in the grid and hover over a face that has not been named yet.  If the face has been recognized, you will see a circle around the face with a text box to name the person.  It may even have a suggested name.

 

Ashampoo_Snap_2019.12.29_11h13m03s_001_.png

If a circle does not appear, double-click on the photo to make it zoom to single image view.  A Mark Face button will now appear in the tool box:

 

Ashampoo_Snap_2019.12.29_11h14m39s_002_.png

Click on it.  If FR has not yet been completed on the photo, you will see an error message telling you that the analysis is not yet complete and (I think) you will be asked whether analysis should be completed.  If FR has been completed but the face has not been found, a bounding box  will appear that you can click and drag over the face.  Once you affirm the location of the face, the naming circle will appear.

 

FR gets better every year but it is not perfect.  I believe that the best method for naming people is to use the UnNamed People tab.  One reason why you may not be seeing all of your faces there is because they may be in small stacks.  Have you tried unchecking the Hide Small Stacks box in the top left of the window.  It is on by default and is easy not to notice.

 

Ashampoo_Snap_2019.12.29_11h25m34s_003_.png

 

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
Dec 29, 2019 Dec 29, 2019

Copy link to clipboard

Copied

Dear Greg,

thank you very much for your help. I followed your instructions (mark face button, bounding box etc.) for all the photos which I dragged and dropped before, and when I clicked on the ppl tab, I saw the generic icons for a sec or so and then they got automatically replaced by the face I manually marked. Problem solved!

(In a way, it makes sense that generic icons appear as they appeared because if Organizer does not recognize the face, it cannot know what to display there - maybe the complete photo would be a better idea though rather than a generic icon.)

Anyway, the drawback of your solution is: It takes ages to do it manually (I guess this is no news for you), and there are many pictures I'd have to do manually. Hence, my questions I did not find answers to it so far:

1. Is the 2020 face recognition algorithm self-learning, so getting better with those people I am helping it with?

2. Is there any Adobe application that has a better algorithm or is it all the same acrosse their apps? I understand, that the cloud services use Adobe Sensei, and on the Elements marketing site it says FR is "based on", "supported by", "powered by" Sensei. Is FR within Elements the same as Sensei or is it worse?

3. How can the FR progress be seen? I found in another post of yours the hint to count the number of json files in the face analysis folder in the catalog; this is 53 items less than media items in the catalog (there are more than 53 videos in the catalog, so this cannot be the cause for the difference). If one face in a picture is recognized, but the second is not, does it necessarily mean that I have to do the second manually because the algorithm is finished with the picture or is this consequence not always true?

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Expert ,
Dec 29, 2019 Dec 29, 2019

Copy link to clipboard

Copied

Yes, the algorithm is self-learning.  The more faces you confirm of a single person, the more FR recognizes that person.  But, as I say, it is not perfect, and it has difficulty picking up which of my two grandsons is which, particularly when they were younger.

 

I don't know whether Lightroom uses a different algorithm or not.  I didn't like the FR interface so have not used it much.  As I understand it, Elements uses "Sensei", but I believe that the FR technology is actually licensed from a third party.

 

Elements 2020 analyzes photos first before turning to analysis of video.  The following status will appear when the analysis is ongoing:

 

Ashampoo_Snap_2019.11.24_22h37m50s_003_.png

You haven't mentioned whether you were aware of the Hide Small Stacks checkbox.  Did that exose more photos for you in the UnNamed People tab?

 

As for the speed of tagging, I have been using the program for many years and I became very adept at quickly selecting and tagging photos.  In the early days of FR (which started in Elements 11 I believe), I could tag my photos faster manually.  But, now, the program is so efficient that it is much faster for me to use the UnNamed People room to tag faces even though there may be many thousands of stacks of irrelevant faces.

 

 

 

 

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
May 17, 2020 May 17, 2020

Copy link to clipboard

Copied

I just noticed when I wanted to read your answer a second time, that I never answered your question regarding the Small Stacks - sorry for that: Yes, it exposed more pictures, quite a lot actually. (Unfortunately, by far, not all with faces on them. So I have to do it manually with "Mark Face" button)

 

In addition: You say that you are quite fast with the UnNamed people room. I see what you mean in terms of adding names to pictures in this room, but when it comes to telling Elements that it should disregard a specific (set of) picture(s), it is a lot if clicks, isn't it? You have to click the picture in the overview, click the picture againg in the lower part of the screen, click "Don't show this again", press enter. Am I missing something?

 

Many thanks in advance,

Ben

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Expert ,
May 18, 2020 May 18, 2020

Copy link to clipboard

Copied

You say that you are quite fast with the UnNamed people room. I see what you mean in terms of adding names to pictures in this room, but when it comes to telling Elements that it should disregard a specific (set of) picture(s), it is a lot if clicks, isn't it? You have to click the picture in the overview, click the picture againg in the lower part of the screen, click "Don't show this again", press enter. Am I missing something?

You can also select multiple stacks and use a right-click context menu to Don't show again.  I find this to be faster with less movement of the mouse cursor.

Ashampoo_Snap_2020.05.18_11h26m30s_002_.png

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
May 18, 2020 May 18, 2020

Copy link to clipboard

Copied

Thanks a lot, Greg, this is going to save me a lot of time. And to be honest, this is in some way quite straight forward...

 

In this context with respect to your hint to use the Mark Face button instead of simply tagging images with names: Do I miss something or does the Mark Face action actually involve a lot of clicks?

1. Click Mark Face (there doesn't seem to be any keyboard shortcut for it)

2. Move and resize (with the latter being a hassle as only a very small area of mouse positions is allowed to get the resize handle) the square.

3. Click add name

4. Type in the first letter, cursor to pic suggestion.

5. Click the green checkmark (enter does not seem to work)

6. Cursor to the next picture.

 

I stopped the time and it is hard to stay way below 10 s, which gives like 170 hours for only 1'000 pictures with one person on it.

 

Hence, I would be really grateful if you happen to have shortcuts here, too? Also, I don't know how to restart the FR algorithm once I tagged say 100 pictures manually which should improve its skills so that after a re-run, the algorithm should be able to tag more pictures than before.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Expert ,
May 18, 2020 May 18, 2020

Copy link to clipboard

Copied

There are no shortcuts for Marking Faces.  However, if you are using the other features of FR, this should involve minimal time.  Yes, many faces are not recognized for a variety of reasons.  But in the grand scheme of things, these should make up a very small minority of the faces in your photos.

 

As for resetting face recognition, this is done in the Preferences>Media Analysis dialog.  But you will lose all FR work completed previously.  So, it's not something I would recommend doing.  AFAIK, it will not recognize any faces that were not previously recognized, it will restore all the faces that you don't want to see again, and you will have to start naming all faces from scratch. 

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
May 20, 2020 May 20, 2020

Copy link to clipboard

Copied

What do you mean by "other" features of FR? I am using it as discussed in this thread: automatic scan, then naming faces and hiding the ones I don't want to name. Is there more to it?

 

What you said about resetting was also my understanding, which is why I used the term of "restarting" rather than resetting as resetting is certainly undesired due to your reasons given. I am thinking of the following example that occurs actually quite often in my picture library:

 

A set of very similiar pictures, all of them not being recognized by FR. So if I then manually mark one and could re-run FR, then it should be a very easy task for FR to automatically mark the other pictures. This corresponds to the self-learning capability of the algorithm that you mentioned earlier in this discussion.

 

Or are you referring to the self-learning feature only when it comes to new pictures that have not been processed (and not recognized) by the algorithm before? This would mean that the only way to re-run FR is to delete the pictures from the catalog and to import again, so the workaround-workflow would be:

 

1. Import new pictures, let FR run (it starts automatically anyway).

2. Do the minimum manual work on face marking: UnNamed Faces room, manual marking of faces not recognized as faces in one picture of all sets with similiar pictures.

3. Delete all new pictures from catalog which have been imported in step 1.

4. Import all new pictures from step 1 again. Via automatic start of FR and its self learning capability it should again recognize everything it recognized in step 1 and, on top of it, all manual work of step 2 should not any more be necessary as the work of step 2 is stored in this catalog's FR information so these "manual marked pictures" of step 2 should now be automatically recognized. Plus, based on this information, it should recognize way more faces than it did in step 2.

5. Do this procedure again until all faces are recognized.

 

This would be quite elaborate for a simple button "re-run FR" (on all catalog pictures or a previously selected subset), but according to my understanding of what you said about FR so far, it should do the job, shouldn't it? What do you think out of your extensive experience with FR about it?

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
May 22, 2020 May 22, 2020

Copy link to clipboard

Copied

Neb1 said:

 

1. Import new pictures, let FR run (it starts automatically anyway).

2. Do the minimum manual work on face marking: UnNamed Faces room, manual marking of faces not recognized as faces in one picture of all sets with similiar pictures.

3. Delete all new pictures from catalog which have been imported in step 1.

4. Import all new pictures from step 1 again. Via automatic start of FR and its self learning capability it should again recognize everything it recognized in step 1 and, on top of it, all manual work of step 2 should not any more be necessary as the work of step 2 is stored in this catalog's FR information so these "manual marked pictures" of step 2 should now be automatically recognized. Plus, based on this information, it should recognize way more faces than it did in step 2.

5. Do this procedure again until all faces are recognized.

Forget about it, at least on a small scale... 😞

 

I did just that with a new test catalog and 63 pictures, which were in my original catalog only partially recognized by FR and including 3 sets of approx. 7 very similiar pictures which were not recognized by FR.

 

So, as described, after importing and automatic FR with applying names and cleaning the UnNamed faces room, I applied the Mark Face thing on one picture on each of the 3 sets. Then I deleted the pictures from the catalog, imported again and FR didn't even recognize the pictures I face marked by hand and as a consequence of course also not the other similiar pictures. This would explain, why there is no simple "re-run FR" button.

 

Additionally, one can read Adobe's help page in a similiar way: In the paragraph about resetting FR, it just says that the consequence is that it starts all over again and you have to name again. So either this article is poorly written as it does not state the important consequence that all self-learned skills disappear after, or there aren't any that can disappear on resetting.

 

So I have to doubt the self-learning capability, unfortunately...

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Expert ,
May 21, 2020 May 21, 2020

Copy link to clipboard

Copied

By "other features," I mean using the UnNamed People room to add names to stacks of recognized faces, using Don't Show Again feature to ignore faces that are not going to be named, and Confirming faces in the Named People room under the "Is this X" dialog.  This, for me, is the most efficient way to tag People.  I occasionally also add names in the Media grid.

 

As for deleting photos and importing them again to improve FR, I don't think that would be of any use.  Face recognition is just that - recognizing a face within a photo and identifying its size and location within a photo.  Adding a name to a face does not change the program's ability to recognize whether or not there is a face in the photo.  Nor does deleting and reimporting a photo after another recognized face of the same person has been identified improve the process.  As I understand it, once you add a name to a stack of photos, if you open the Add Name text box of another stack of the same person, a name/names will be auto-suggested for that person.  Also, in this situation, if you go to the Named People room, there may be a blue triangle next to the identified person's stack, and if you open that named person's stack, you will see suggestions of other photos of that person ready for confirmation.  Those "is this X" confirmations are for photos that the program now thinks is the same person based on your naming that person.  If you confirm the face here, the same photo of that person will be removed from a stack in the UnNamed People room.

 

The only reason I can think of for deleting and reimporting a set of photos is if you have mistakenly hit the Don't Show Again button/command.  In that case, the face will be removed from consideration as a recognized face and would need to be imported again for the face to be recognized.  (Or the Mark Face tool can be used to add the face manually.)

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
May 21, 2020 May 21, 2020

Copy link to clipboard

Copied

Thanks for your fast response.

 

Greg_S. said:

By "other features," I mean [...]

 

Good to hear, as this means that I am already using all the features that FR offers and that help FR in automatically recognizing as many pictures as possible.

 

Greg_S. said:

I occasionally also add names in the Media grid.

 

OK, this might explain our different perception of how much the user has to spend for marking faces. I understood from earlier posts in this thread that adding names in the Media grid is not the ideal solutions as this leads to grayed out icons and does not improve the algorithm's skills (via self-learning) so I understood the only "true" option is Mark Face, which takes orders of magnitude longer than plain taggingof (multiple) pictures in the media grid.

 

Greg_S. said:

Face recognition is just that - recognizing a face within a photo and identifying its size and location within a photo. Adding a name to a face does not change the program's ability to recognize whether or not there is a face in the photo.

 

Just to avoid misunderstandings: In my step 2 with "manual marking of faces not recognized" I was not referring to tagging in the media grid but to Marking Faces. In this process you tell the program the "size and location" of a face within a picture just as you wrote and not just simply adding a name to picture. Given your earlier sentence "Yes, the algorithm is self-learning. The more faces you confirm of a single person, the more FR recognizes that person." it is not obvious to me why you think that the 5 steps given above should not lead to better FR results, as you could regard the Mark Face thing also as a "confirmation" in your words that person X is in this picture which should help the FR algorithm, shouldn't it?

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Community Expert ,
May 21, 2020 May 21, 2020

Copy link to clipboard

Copied

I understood from earlier posts in this thread that adding names in the Media grid is not the ideal solutions as this leads to grayed out icons and does not improve the algorithm's skills (via self-learning) so I understood the only "true" option is Mark Face, which takes orders of magnitude longer than plain taggingof (multiple) pictures in the media grid.

There is also the option to hover over a recognized face in the grid and add a name there.

 

you could regard the Mark Face thing also as a "confirmation" in your words that person X is in this picture which should help the FR algorithm, shouldn't it?

It seems to me that you only need to use Mark Face when the program can't even recognize that a face exists in the photo.  This can be for a variety of reasons, including lighting and shadows, the angle of the face/body, glasses or goggles, hats and scarves - and in this day and age: face masks.  So adding a name to something that the program only sees as an unidentified blob does not necessarily mean that the algorithm will identify another blob as a face and certainly not a face belonging to X.  Perhaps AI does a better job than I think.  But I can't imagine that it is relying on users repeatedly deleting and importing the same set of photos.

 

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
Explorer ,
May 21, 2020 May 21, 2020

Copy link to clipboard

Copied

Greg_S. said:

There is also the option to hover over a recognized face in the grid and add a name there.

 

I guess this is just another way of doing the same as in the UnNamed people room, i. e. if no more open faces are pending in UnNamed people room, you won't find anything to hover over in media grid, correct? Additionally, I cannot think of a scenario where the hover-approach would be faster than Unnamed people room, can you?

 

Greg_S. said:

So adding a name to something that the program only sees as an unidentified blob does not necessarily mean that the algorithm will identify another blob as a face and certainly not a face belonging to X. Perhaps AI does a better job than I think.

 

"Not necessarily" is true, for sure. But my understanding of the term "self-learning" / "AI" that you also used is, that similiar blobs to the blob which are manually identified as a help to the algorithm are then more likely to be identified (the question was about a stack of similiar pictures not being recognized) and with the algorithm taught a lot of different blobs the new blobs can be more different from the previous ones and the algorithm is more likely to identify also this one. This is, I guess, also why you say that FR is getting better with each "Is this X dialog", isn' it?

 

Greg_S. said:

But I can't imagine that it is relying on users repeatedly deleting and importing the same set of photos.

 

I think here is another basic misunderstanding: My whole question is not about letting the algorithm run several times over the same pictures with no difference in between the runs. I fully agree, this is not likely to be of any help.

 

My approach was to give new information to the algorithm in between the runs as given in step 2: using the UnNamed People room to add names to stacks of recognized faces, Confirming faces in the Named People room under the "Is this X" dialog and manual marking of faces (via Mark Face) not recognized as faces in one picture per set with similiar pictures and then let it run again. You see what I mean?

 

Sorry to stretch this topic a lot, but I think it gives in addition to Adobes manual a really good overview of the FR workflow and thus can save people a lot of time.

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
New Here ,
Aug 20, 2021 Aug 20, 2021

Copy link to clipboard

Copied

LATEST

Browse

Votes

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines