Bug 409995 - Scan for Faces in video files is not yet supported
Summary: Scan for Faces in video files is not yet supported
Status: REPORTED
Alias: None
Product: digikam
Classification: Applications
Component: Faces-Detection (show other bugs)
Version: 7.9.0
Platform: unspecified Microsoft Windows
: NOR wishlist
Target Milestone: ---
Assignee: Digikam Developers
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2019-07-19 12:55 UTC by Tor
Modified: 2023-02-26 10:28 UTC (History)
4 users (show)

See Also:
Latest Commit:
Version Fixed In:


Attachments

Note You need to log in before you can comment on or make changes to this bug.
Description Tor 2019-07-19 12:55:56 UTC
SUMMARY
I hope you soon will add the support for "Scan for Faces" in video files. If so, do you have an ETA on that? Thanks.

STEPS TO REPRODUCE
1. Import video files
2. Scan for Faces
3. No faces are detected (It works with picture files, so it is turned on)

OBSERVED RESULT
Does not find faces in video files

EXPECTED RESULT
Some faces in "People" should show up for me to name.

SOFTWARE/OS VERSIONS
Windows: 10

ADDITIONAL INFORMATION
Hope you will add this as I hope to get away from Google Photos solution next coming months/years...
Comment 1 MarcP 2019-07-24 15:54:28 UTC
Not a dev, but there is a project to improve the whole face recognition process in digikam. However, I have not heard anything about recognizing people in videos, so I wouldn't be optimistic about it, at least in short-medium term.

Probably some of the developers will be able to give you a more specific answer.
Comment 2 caulier.gilles 2019-07-29 09:20:40 UTC
A quick response from me :

Video face detection will be time consuming. You need to read frame by frame (in critical case) to check if a face exist in image. So the video need to be decompressed and analyzed.

Second point, we need a temporal property to add in database to localize a face in a specific frame from a video. This kind of value do not exist yet in database.

Anyway, detection and recognition algorithm do not needs to be adjusted for video as media is analyzed by frames (images).

Gilles Caulier
Comment 3 Minh Nghia Duong 2020-08-19 23:55:28 UTC
Real-time face detection and recognition on video are possible. However, if you wish to extract all the faces appear in the video, it is possible that too many faces are returned, depend on the number of frames. If you wish to return only distinct faces in the video, face clustering is needed. 

In both ways, video analyse like this, as Gilles said, is time-consuming. But if this feature is still in need, I could try to implement it
Comment 4 Andrei 2023-02-26 10:28:01 UTC
About time. I don't see problem with it. I can run it at night.

But I see another problem with shouldn't be done before: to see similar faces as one with some coefficient.