Clemens Neudecker

ocr-conversion. Conversions between various OCR formats

ocr-gt. OCR & Ground Truth Resources

alto-tools. Python tools for performing various operations on ALTO XML files

alto-ocr-text. extract text from ALTO file

hip21_ocrevaluation. A Survey of OCR Evaluation Tools and Metrics (HIP'21)

ner-corpora. Named Entity Recognition corpus for (historical) Dutch, French, German

page-to-text. extract text from PAGE file

alto-ocr-confidence. calculate OCR confidence per page in ALTO

layout_gallery. vDHd2021 experiment

web-wf-design. Forked from http://code.google.com/p/taverna/source/browse/portal/web-wf-design/trunk/web-wf-design/ for experimenting

newspaper-page-classification. Fast classification of newspaper pages using fastai