Forgive my ignorance, but I’ve got a question concerning OCR tools. Until now, I have utilized a paid service to upload, scan, convert them to searchable documents, and store my handwritten Uni notes. Handwritten because, frankly, my brain seems to engage with the content “better” than by digital note-taking.
It worked fine for what I needed, so I have never investigated open-source or had actual ownership/control over my uploaded notes before. As my work expands and the database of notes grows, maintaining data privacy is a huge concern, and I do not want to use the same system for interviews and such. My Uni has been, well, unhelpful sadly.
Are there any recommendations for having a similar system that puts more control and privacy in my hands?
Handwriting has been proven to enhance learning in humans, so you are doing great by keeping the habit!
I don’t have much to recommend, but so far this little tool was very useful for me and my math studies: https://github.com/lukas-blecher/LaTeX-OCR
I am not a student, but I learn like a student all the time. I also enjoy handwriting (got an e-ink tablet for that) and knowledge management. I am often dreaming of a “perfect setup” where all I write gets pushed automatically through OCR into my knowledge vault (Obsidian, Logseq or whatever I/my peers happen to use). Even came up with a plan. I hope this new year will leave me enough energy to execute something useful.
Would you like to collaborate on that perhaps?
I appreciate your answer; give me time to research what you’ve laid before me and get back to you. Feel free to ping me (PM? DM? I’m new here) to discuss further. I am starting from 0 on this one, including having little to no knowledge of Obsidian beyond “Hey, that exists.”
I work in a digitalisation environment, we use OCR in different ways, sometimes with tesseract and sometimes with adobe. Both are differently effective. Tesseract needs training and adobe has mostly a propetary better recognition. Handwriting is mostly a special part which needs manual control.
In my private environment I use a mix with paperless-ngx (which only does tesseract-ocr if it doesn’t is already OCR recognised). Paperless is able to change and export the output of the PDFs in a json database which I partly convert to trilium (a database based notebook).
Didn’t found a better solution yet and it isn’t mostly not handwritten.
I have some reading and learning to do, and I appreciate your reply.
Thank for for the great responses so far. I’ve encountered some limitations due to university provided laptop (Power/OS of Windows 11) and my own coding inexperience. However, I am exploring a setup that employs Docker and Paperless NGX. I’ve yet to upload hand written notes in PDF format, but as captured via a phone camera the OCR is abysmal. For typed PDF, the OCR is perfect. It parsed through, with no errors, a 100 page contract document and provided the text for import into an analytical program.