Skip to content

Latest commit

 

History

History
6 lines (5 loc) · 366 Bytes

README.md

File metadata and controls

6 lines (5 loc) · 366 Bytes

Vision Related Task

1. Text Extraction:

Applied pytesseract pretrained model of open-cv to these photos. To run in command/terminal: python text_recognition.py --east path/frozen_east_text_detection.pb --image path/file_name For padding: python text_recognition.py --east path/frozen_east_text_detection.pb --image path/file_name --padding float_value