[digikam] [Bug 495540] Accuracy of the auto tag feature is very bad
https://bugs.kde.org/show_bug.cgi?id=495540 --- Comment #3 from cvinhaes --- (In reply to Michael Miller from comment #2) > Hello, > Yes, the current AI models for object detection for automatic tagging need > to be updated. There are newer models that give better results. We're > focusing on improving face detection and recognition in this release. We > may be able to add some new auto-tagging AI models in the 8.5.0 release, but > it may have to wait until 8.6.0. Please know we also think that > auto-tagging could be better, and it's on our list of improvements. > > As Gilles asked, what are you using now? > > Cheers, > Mike Thank you for your quick response. If you mean with DigiKam, I have tested with YOLO Nano v5 and ResNet50. If you mean to what I am comparing Digikam to, that is Photoprism,which adopts NASNet Mobile 224 , I think. Photoprism is way more conservative but yeld more reliable results overall. Both aplications are connected to the same set of photos. -- You are receiving this mail because: You are watching all bug changes.
[digikam] [Bug 495540] New: Accuracy of the auto tag feature is very bad
https://bugs.kde.org/show_bug.cgi?id=495540 Bug ID: 495540 Summary: Accuracy of the auto tag feature is very bad Classification: Applications Product: digikam Version: 8.4.0 Platform: Microsoft Windows OS: Microsoft Windows Status: REPORTED Severity: minor Priority: NOR Component: Tags-AutoAssignement Assignee: digikam-bugs-n...@kde.org Reporter: k...@cvinhaes.33mail.com Target Milestone: --- SUMMARY I've stated to play around with automatic tagging using the maintenance tools and the result are underwhelming. I have collection of 100K+ photos and most keywords assigned are way off, specially when compared to the job done by Photoprism or Immich. I have tested with all available models and , while the level of detail found in the tags will change, the accuracy remains very poor in all cases. STEPS TO REPRODUCE 1. Maintenance tools 2. Auto-tag assignment 3. OBSERVED RESULT Tagging starts as expected and take a long time to complete. Tags are nested under the 'auto' tag. Checking the photos found under each tag using the filter option, most of the photos are completely unrelated to the word described by the tag. EXPECTED RESULT The same, but with better accuracy. I don't expect to select pictures tagged as 'airplane' and find shots of people walking on the streets. SOFTWARE/OS VERSIONS Windows: 10 macOS: (available in the Info Center app, or by running `kinfo` in a terminal window) Linux/KDE Plasma: KDE Plasma Version: KDE Frameworks Version: Qt Version: ADDITIONAL INFORMATION -- You are receiving this mail because: You are watching all bug changes.
[digikam] [Bug 486298] New: Feature request: Allow one-to-many search for duplicates
https://bugs.kde.org/show_bug.cgi?id=486298 Bug ID: 486298 Summary: Feature request: Allow one-to-many search for duplicates Classification: Applications Product: digikam Version: 8.3.0 Platform: Microsoft Windows OS: Microsoft Windows Status: REPORTED Severity: normal Priority: NOR Component: general Assignee: digikam-bugs-n...@kde.org Reporter: k...@cvinhaes.33mail.com Target Milestone: --- SUMMARY FEATURE REQUEST: restrict duplicate image search in Similarity to have one folder or a group of folders as the 'mandatory reference' folder(s), i.e. photos would just be considered duplicate if they exist in the 'mandatory reference' set of folders. As implemented today, duplicates are also found between folders which are NOT listed in the 'prefer selected folder as reference' because, in the absence of duplicates in the folders selected as reference, Digikam will pick another folder as reference. By implementing mandatory reference folder(s), the photos would only be tagged as duplicates if they DO exist in the mandatory set and Digikam would skip duplicates between non-mandatory folders. Use case: Allow one-to-many search for duplicates - compare folder 'X' to a list of folders and check if there are duplicates between folder X and the provided list of folders. SOFTWARE/OS VERSIONS Windows 10 DigiKam 8.3.0 -- You are receiving this mail because: You are watching all bug changes.
[digikam] [Bug 441648] preview of next/previous HEIF (iPhone) image is very slow
https://bugs.kde.org/show_bug.cgi?id=441648 --- Comment #24 from cvinhaes --- Same result here, excruciatingly slow times to refresh the preview for .heif files. Win10 with 16gb ram. -- You are receiving this mail because: You are watching all bug changes.
[digikam] [Bug 441648] preview of next/previous HEIF (iPhone) image is very slow
https://bugs.kde.org/show_bug.cgi?id=441648 cvinhaes changed: What|Removed |Added CC||k...@cvinhaes.33mail.com -- You are receiving this mail because: You are watching all bug changes.
