AI for Historical Document Analysis

3A-D20

Project 3A-D20 - An Archive Automation-Decoder 2.0

Requirements

Python 3.7.1

OpenCV-Python 4.2.0

Tesseract 4.1.1

Leptonica 1.79.0

PyTesseract 0.3.4

Pandas 1.0.4

NumPy 1.18.0

Matplotlib 3.2.1

Traineddata used for test

  • eng - English

  • enm - English, Middle (1100-1500)

  • ita - Italian

  • ita_old - Italian - Old

  • lat - Latin