Tesseract is an optical character recognition engine for various operating systems.[2] It is free software, released under the Apache License, Version 2.0,[1][3][4] and development has been sponsored by Google since 2006.[5] Tesseract is considered one of the most accurate open-source OCR engines currently available.[4][6]
https://tpgit.github.io/Leptonica/struct_boxa.html