essentiasoftserv / openbharatocr

openbharatocr is an opensource python library which facilitates extracting data from official indian government documents
Apache License 2.0
4 stars 8 forks source link

Dergree Certificate Testing #49

Closed Rishabh0411 closed 2 days ago

Rishabh0411 commented 4 weeks ago

Regressive Testing for The Degree Certificate Module Make an excel sheet stating which sample is failing on which function and passing on which function Main issues:- Pytesseract is having trouble in extracting text from images with different fonts. Some degrees mentioned year of passing in words so it is not extracting them. In some samples the images pytesseract is not extracting anything or just university name and in some it is extracting partial information.

Rishabh0411 commented 4 weeks ago

Hi, Currently working on the same