ocrmypdf
Searching math equations
This is not an issue just a feature request.
It will be awesome if math equations and formulas were converted to latex expressions. When highlighting or searching for a formula, search by latex or copy latex. Not sure the difficulty of this task but it will be very useful.
It is possible to use Tesseract with the pseudo-language "equ" for equation detection. You could do ocrmypdf -l eng+equ for that (English + "equation language). I have not tried this before and I don't think it attempts to translate them to a latex representation. I'd be curious to hear how it works.
It sounds really interesting but I don't think I'd be able to seriously consider a project of that size unless someone were prepared to sponsor it.
The equ language has been removed from Tesseract 4+: https://github.com/tesseract-ocr/tessdata_fast/issues/4#issuecomment-572740279
