0

I want to use the HOCR that I get from TesseractJS (I work on Javascript) and somehow transform it to be readable by a LLM. The goal is to reade technical documents with prices, tabs, header, lines, footer... not just a normal text.

Currently, I plan to "transform" the hOCR to a structured text, but I don't know how yet..

Any idea or anything else ?

Improve this question
Related questions
220
image processing to improve tesseract OCR accuracy
141
Could not initialize tesseract
91
Limit characters tesseract is looking for
Load 6 more related questions Show fewer related questions

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.