β² 823 βΌ Not Total Recall (1990) (lemmy.world) submitted 2 years ago* by ordellrb@lemmy.world to c/linuxmemes@lemmy.world 64 comments fedilink hide all child comments
[β] R00bot@lemmy.blahaj.zone 21 points 2 years ago (3 children) I can't imagine it'd be that hard to write some code that does that using an existing AI model. permalink fedilink source parent hideshow 6 child comments replies: [β] not_amm@lemmy.ml 9 points 2 years ago I found a small command to run KDE Spectacle (screenshot software) with Tesseract so I can OCR a screenshot if I want to, I only had to install Tesseract and a main language, you could easily do the same with an API and/or a local AI. permalink fedilink source parent [β] JackGreenEarth@lemm.ee 5 points 2 years ago You're probably right. permalink fedilink source parent [β] MacNCheezus@lemmy.today 3 points 2 years ago Llava and Bakllava are two Ollama models than can not only extract text but also describe what's happening on screen. Using tesseract-ocr, as the other guy suggested, is probably simpler and less resource intensive though. permalink fedilink source parent
[β] not_amm@lemmy.ml 9 points 2 years ago I found a small command to run KDE Spectacle (screenshot software) with Tesseract so I can OCR a screenshot if I want to, I only had to install Tesseract and a main language, you could easily do the same with an API and/or a local AI. permalink fedilink source parent
[β] JackGreenEarth@lemm.ee 5 points 2 years ago You're probably right. permalink fedilink source parent
[β] MacNCheezus@lemmy.today 3 points 2 years ago Llava and Bakllava are two Ollama models than can not only extract text but also describe what's happening on screen. Using tesseract-ocr, as the other guy suggested, is probably simpler and less resource intensive though. permalink fedilink source parent
