Using OCR text recognition on UFA Super8 film catalogues

Data sets and files in this repository are supplemented by the project documentation under the following link:

https://demo.hedgedoc.org/s/13POm74xu

This repository contains:

1. Several folders containing sample variations

a. sample_tesseract_JPG

b. sample_tesseract_TIFF

c. sample_tesseract_COVER

d. sample_OCR4all_default

e. groundtruth

2. Jupyter Notebooks containing python script for evaluating different workflows

a. sample_OCR4all_default.ipynb

b. sample_tesseract_COVER.ipynb

c. sample_tesseract_BLACKLIST.ipynb

d. sample_tesseract_JPG.ipynb

e. sample_tesseract_TIF.ipynb

3. Evaluation Visualisation

a. plot_tesseract_COVER

b. plot_tesseract_JPG

c. plot_tesseract_TIF

d. plot_OCR4all_default

4. README.md

5. LICENSE.md

Extra: db_transfer.ipynb