This file briefly describes the folders in the OCRopus structure. There are READMEs in each folder that give a bit more details. commands -- some small top-level C++ programs data -- document images, language models and trained data doc -- documentation evaluation -- scripts for evaluating OCRopus ext -- external dependencies of OCRopus imgbits -- advanced image processing langmods -- language modelling ocr-binarize -- preprocessing: functionality for binarization ocr-bpnet -- classification: neural network ocr-deskew-rast -- preprocessing: deskewing ocr-doc-clean -- preprocessing: document image cleanup ocr-layout-rast -- layout analysis ocroscript -- OCRopus scripting, also contains quite some scripts ocr-pageseg -- layout-analysis: page segmentation ocr-samples -- simple example implementations ocr-tesseract -- classification: tesseract ocr-utils -- central utilities python-binding -- self-explanatory utilities -- utilities for checking / testing OCRopus software