NihalPotdar / ConvertToText

Command line tool/ python library to convert handwritten files directly to an excel file

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ConvertToText

Command line tool/ python library that implements handwriting analysis with a data pipeline, to convert handwritten forms into a column format on excel. The data pipeline and related files can be found in preprocess.py, the handwriting analysis implementation under detect.py, and the excel conversion under write_to_excel.py.

Tech Stack: Google Vision API, Pandas, OpenCV.

TODO

Implement NLU with a BERT model to replace regex for form field detection.

About

Command line tool/ python library to convert handwritten files directly to an excel file


Languages

Language:Python 100.0%