Description
Full Time (8 Weeks)
Supervised by: Brahmabit Biswas
- Developed a Python pipeline to extract text from images on receipts and invoices, using OpenCV and Google’s Tesseract engine
- Created a corupus out of the extracted test for NLP
- Performed Named Entity Recognition using SpaCy in Python to create completely digitized versions of the input invoice images
Knowledge
- Data Science
- Machine Learning
- Computer Vision
- NLP
Skills
- Python
- OpenCV
- SpaCy