search

robertknight / ocrs

Rust library and CLI tool for OCR (extracting text from images)
Apache License 2.0
1.09k stars 44 forks source link

Could this be used to extract tabular data from photos of supplements? #47

Closed lilouartz closed 3 months ago

lilouartz commented 4 months ago

0108_nowproductlabels

My dataset are photos such as this one.

I am looking for a software that could extract tabular information from these photos.

Is this a good use case for ocrs?

robertknight commented 4 months ago

Ocrs can read the words and provide their location in the image, but it can't determine whether a word is part of a table and which cell/row it belongs to, so you would need to write code to do that. There is a general issue about table support at https://github.com/robertknight/ocrs/issues/39.