This software implements a heavily parallelized pipeline to recognize text in PDF files. It is used for nopaque's OCR service but you can also use it standalone, for that purpose a convenient wrapper script is provided.

Software used in this pipeline implementation

Official Debian Docker image (buster-slim): https://hub.docker.com/_/debian
- Software from Debian Buster's free repositories
ocropy (1.3.3): https://github.com/ocropus/ocropy/releases/tag/v1.3.3
pyFlow (1.1.20): https://github.com/Illumina/pyflow/releases/tag/v1.1.20
Tesseract OCR (4.1.1): https://github.com/tesseract-ocr/tesseract/releases/tag/4.1.1
tessdata_best (4.1.0): https://github.com/tesseract-ocr/tessdata_best/releases/tag/4.1.0

Use this image

Create input and output directories for the pipeline.

mkdir -p /<my_data_location>/input /<my_data_location>/output

Place your PDF files inside /<my_data_location>/input. Files should all contain text of the same language.
Start the pipeline process. Check the Pipeline arguments section for more details.

# Option one: Use the wrapper script
## Install the wrapper script (only on first run). Get it from https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr/-/raw/development/wrapper/ocr, make it executeable and add it to your ${PATH}
cd /<my_data_location>
ocr -i input -l <language_code> -o output <optional_pipeline_arguments>

# Option two: Classic Docker style
docker run \
    --rm \
    -it \
    -u $(id -u $USER):$(id -g $USER) \
    -v /<my_data_location>/input:/input \
    -v /<my_data_location>/output:/output \
    gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/ocr:development \
        -i /ocr_pipeline/input \
        -l <language_code> \
        -o /ocr_pipeline/output \
        <optional_pipeline_arguments>

Check your results in the /<my_data_location>/output directory.

Pipeline arguments

Mandatory arguments

-i, --input-dir INPUT_DIR

Input directory

-o, --output-dir OUTPUT_DIR

Output directory

-l, --language {spa,fra,dan,deu,eng,frm,chi_tra,ara,enm,ita,ell,frk,rus,por}

Language of the input (3-character ISO 639-2 language codes)

Optional arguments

--binarize

Add binarization as a preprocessing step

--log-dir

Logging directory

--mem-mb

Amount of system memory to be used (Default: min(--n-cores * 2048, available system memory))

--n-cores

Number of CPU threads to be used (Default: min(4, available CPU cores))

-v, --version

Returns the current version of the OCR pipeline

# Example with all arguments used
docker run \
    --rm \
    -it \
    -u $(id -u $USER):$(id -g $USER) \
    -v /<my_data_location>/input:/ocr_pipeline/input \
    -v /<my_data_location>/output:/ocr_pipeline/output \
    -v /<my_data_location>/logs:/ocr_pipeline/logs \
    gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/ocr:development \
        -i /ocr_pipeline/input \
        -l eng \
        -o /ocr_pipeline/output \
        --binarize \
        --log-dir /ocr_pipeline/logs \
        --n-cores 8 \