Bug 432412

Summary: Training Face recognition for blur and pixellation
Product: [Applications] digikam Reporter: Paul <paulpuaux>
Component: Faces-DetectionAssignee: Digikam Developers <digikam-bugs-null>
Status: RESOLVED DUPLICATE    
Severity: wishlist CC: metzpinguin
Priority: NOR    
Version First Reported In: unspecified   
Target Milestone: ---   
Platform: macOS (DMG)   
OS: macOS   
Latest Commit: Version Fixed/Implemented In:
Sentry Crash Report:

Description Paul 2021-02-02 10:34:36 UTC 
SUMMARY

Offering visual UX method to exclude from face recognition faces too blurred or too pixelated, using Deep Learning

STEPS TO REPRODUCE
1. Adding a button/box with blur/pixel icon
2. In popup window, show on the left an illustrated blur slider to validate a requested sharpness index (i.e. above a blur factor of x)
3. show on the right an illustrated pixel slider to validate a requested precision index (i.e. above a pixel factor of x)

OBSERVED RESULT

Exclude from listing low quality / poorly performing recognized faces


EXPECTED RESULT

Get a more consistent visual face album, less blurred/pixelated results, while maintaining fast accurate recognition.


SOFTWARE/OS VERSIONS
Windows: 
macOS: 
Linux/KDE Plasma: 
(available in About System)
KDE Plasma Version: 
KDE Frameworks Version: 
Qt Version: 

ADDITIONAL INFORMATION
Comment 1 Maik Qualmann 2021-02-02 10:55:32 UTC 

*** This bug has been marked as a duplicate of bug 425263 ***