Hello, Is it possible to add a plugin that enable you to use Google Cloud Vision Api https://cloud.google.com/vision/ so they can automatically tag photo based on the result 1. Select several photo that they want automatically add keyword/tag 2. Select which feature they want (Face Detection, Landmark detection, Logo Detection, Label Detection, Text Detection, Document Text Detection, Image Properties, Objection Detection, Explicit Detection) 3. create copy of and rize the photo to reduce bandwidth size 4. Base64 Encode the photo 5. Send the request to Google Cloud Vision Api 6. Retrieve the JSON Result 7. Insert the json result to tag/keyword of the selected photo. you can also create an option so you can choose manually the tag/keyword to add you can find more info here https://cloud.google.com/vision/docs there are also lightroom classic plugin which use the google cloud vision api that use lua here https://johnrellis.com/lightroom/anyvision.htm sadly i cannot use lightroom because it replaced the created/modified file date the google cloud vision api is free for 1000 photo/month or you can get 300usd free when you add a credit card that works for about 200k photo if u use 1 feature, and there are also Microsoft Computer Vision and Amazon Rekognition that work similar to Google Cloud Vision Api And is there a way to use the lightroom plugin in digikam? thank you
*** This bug has been marked as a duplicate of bug 384444 ***
The double bug report also mentions Google vision. I see the chances as bad as the API is not free to use. I would be happy if Google enabled us to use Google Maps again. Maik
the google cloud vision api is free for 1000 photo/month or you can get 300usd free when you link a credit card that works for about 200k photo if u use 1 feature, i don't think there is a completely free auto tagging/keyword webservice, there are a plugin for darktable that can do local auto tagging/keyword but sadly i cannot try it since it only work for linux/mac
Hi, With next digiKam 8.3.0 release, the auto-tags assignment feature have been implemented but without using a cloud service. In fact digiKam will never use a cloud service to analyze local files, for security/policy/right/performance reasons : local photo must never been shared to the web in background for this kind of processing. The processing is done in core application with delegate neural network models stored in computer. For more details about auto-tags assignment feature, look on student work report : https://community.kde.org/GSoc/2023/StatusReports/QuocHungTran#Add_Automatic_Tags_Assignment_Tools_and_Improve_Face_Recognition_Engine_for_digiKam Best regards Gilles Caulier