Workflow Guide recommendations

In order to facilitate the usage of OCR-D and the configuration of workflows, we provide two workflows which can be used as a start for your OCR-D-tests. They were determined by testing the processors listed above on selected pages of some prints from the 17th and 18th century.

The results vary quite a lot from page to page. In most cases, segmentation is a problem.

Note that for our test pages, not all steps described above werde needed to obtain the best results. Depending on your particular images, you might want to include those processors again for better results.

We are currently working on regression tests with the help of which we will be able to provide more profound workflows soon, which will replace those interim solutions.

Minimal workflow

Since ocrd-tesserocr-recognize can do binarization (Otsu), region segmentation, table recognition, line segmentation and text recognition at once, just like the upstream tesseract command line tool, it's a good single-step workflow to get a baseline result to compare to granular workflows.

Note: Be aware that you will most likely obtain significantly better results by configuring a more granular workflow like e.g. the workflows below.

Step	Processor	Parameter
1	ocrd-tesserocr-recognize	-P segmentation_level region -P textequiv_level word -P find_tables true -P model Fraktur_GT4HistOCR

Example with ocrd-process

ocrd process "tesserocr-recognize -P segmentation_level region -P textequiv_level word -P find_tables true -P model GT4HistOCR_50000000.997_191951"

Best results for selected pages

The following workflow has produced best results for 'simple' pages (e.g. this page) (CER ~1%).

Step	Processor	Parameter
1	ocrd-cis-ocropy-binarize
2	ocrd-anybaseocr-crop
3	ocrd-skimage-binarize	-P method li
4	ocrd-skimage-denoise	P level-of-operation page
5	ocrd-tesserocr-deskew	-P level-of-operation page
7	ocrd-cis-ocropy-segment	-P level-of-operation page
13	ocrd-cis-ocropy-dewarp
14	ocrd-calamari-recognize	-P checkpoint_dir qurator-gt4histocr-1.0

Example with ocrd-process

ocrd process \
  "cis-ocropy-binarize -I OCR-D-IMG -O OCR-D-BIN" \
  "anybaseocr-crop -I OCR-D-BIN -O OCR-D-CROP" \
  "skimage-binarize -I OCR-D-CROP -O OCR-D-BIN2 -P method li" \
  "skimage-denoise -I OCR-D-BIN2 -O OCR-D-BIN-DENOISE -P level-of-operation page" \
  "tesserocr-deskew -I OCR-D-BIN-DENOISE -O OCR-D-BIN-DENOISE-DESKEW -P operation_level page" \
  "cis-ocropy-segment -I OCR-D-BIN-DENOISE-DESKEW -O OCR-D-SEG -P level-of-operation page" \
  "cis-ocropy-dewarp -I OCR-D-SEG -O OCR-D-SEG-LINE-RESEG-DEWARP" \
  "calamari-recognize -I OCR-D-SEG-LINE-RESEG-DEWARP -O OCR-D-OCR -P checkpoint_dir qurator-gt4histocr-1.0"

Note: (1) This workflow expects your images to be stored in a folder called OCR-D-IMG. If your images are saved in a different folder, you need to adjust -I OCR-D-IMG in the second line of the call above with the name of your folder, e.g. -I MAX (2) For the last processor in this workflow, ocrd-calamari-recognize, you need to specify the model which is to be used. If you didn't download it via the OCR-D resource manager, you have to use the checkpoint parameter and pass your local path to the model on your hard drive as parameter value! In this case, the last line of the ocrd-process call above could e.g. look like this:

  "calamari-recognize -I OCR-D-SEG-LINE-RESEG-DEWARP -O OCR-D-OCR -P checkpoint /test/data/calamari_models/\*.ckpt.json"

All the other lines can just be copied and pasted.

Good results for slower processors

If your computer is not that powerful you may try this workflow. It works fine for simple pages and produces also good results in shorter time.

Step	Processor	Parameter
1	ocrd-cis-ocropy-binarize
2	ocrd-anybaseocr-crop
3	ocrd-skimage-denoise	-P level-of-operation page
5	ocrd-tesserocr-deskew	-P level-of-operation page
7	ocrd-tesserocr-segment	-P shrink_polygons true
13	ocrd-cis-ocropy-dewarp
14	ocrd-tesserocr-recognize	-P textequiv_level glyph -P overwrite_segments true -P model GT4HistOCR_50000000.997_191951

Example with ocrd-process

ocrd process \
  "cis-ocropy-binarize -I OCR-D-IMG -O OCR-D-BIN" \
  "anybaseocr-crop -I OCR-D-BIN -O OCR-D-CROP" \
  "skimage-denoise -I OCR-D-CROP -O OCR-D-BIN-DENOISE -P level-of-operation page" \
  "tesserocr-deskew -I OCR-D-BIN-DENOISE -O OCR-D-BIN-DENOISE-DESKEW -P operation_level page" \
  "tesserocr-segment -I OCR-D-BIN-DENOISE-DESKEW -O OCR-D-SEG -P shrink_polygons true" \
  "cis-ocropy-dewarp -I OCR-D-SEG -O OCR-D-SEG-DEWARP" \
  "tesserocr-recognize -I OCR-D-SEG-DEWARP -O OCR-D-OCR -P textequiv_level glyph -P overwrite_segments true -P model GT4HistOCR_50000000.997_191951"

Note: (1) This workflow expects your images to be stored in a folder called OCR-D-IMG. If your images are saved in a different folder, you need to adjust -I OCR-D-IMG in the second line of the call above with the name of your folder, e.g. -I my_images (2) For the last processor in this workflow, ocrd-tesserocr-recognize, the environment variable TESSDATA_PREFIX has to be set to point to the directory where the used models are stored if they are not in the default location. If you downloaded your models with the OCR-D resource manager, this is already taken care of.