Jump to content

Facial Recognition - improment suggestions


rene

Recommended Posts

Dear Daminion Community,

I’ve been thinking about ways we could enhance the Face Recognition feature while reducing the server’s workload.

Facial Recognition by Folder Structure
Instead of applying facial recognition to the entire media library, it would be great to enable it for specific folder structures. For instance, after returning from a trip, I might only want to scan a particular folder. 

Selecting Specific People for Scanning
In a situation like the one above, if I know I was on a family vacation or at a wedding, I could specify the people who were there. This way, Daminion would know which faces to prioritize, helping avoid unnecessary scans. Similarly, after scanning older photos, this feature could help Daminion improve its accuracy over time.

Low-Resolution Scanning

Running initial face detection on lower-resolution previews or thumbnails could save significant processing power and time. Once faces are detected, the system could then zoom in or use higher resolution for identification. This could drastically reduce server workload without compromising accuracy.

Duplicate Image Detection

If Daminion identifies duplicate or highly similar images (e.g., multiple photos from the same event), it could avoid scanning them multiple times. This would reduce the workload by skipping redundant scans.

 

Tell me, do I have a thinking error there?

 

 

All the best

René

Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...