Workflow Guide font detection

These processors can determine the font family (e.g. Antiqua, Fraktur, Schwabacher) to help select the right models for text detection.

Note: ocrd-typegroups-classifier can only annotate font families on page level but can detect a wider variety of fonts, including the confidence value (separated by colon). Supported fontFamily values:

• Antiqua
• Bastarda
• Fraktur
• Gotico-Antiqua
• Greek
• Hebrew
• Italic
• Rotunda
• Schwabacher
• Textura
• other_font
• not_a_font

Note: ocrd-typegroups-classifier only works on non-binarized RGB images.

Note: ocrd-typegroups-classifier comes with a non-OCR-D CLI that allows for the generation of "heatmaps" on the page to visualize which regions of the page are classified as using a certain font with a certain confidence, see the project's README for usage instructions.

Available processors

Processor	Parameter	Remarks	Call
ocrd-typegroups-classifier	-P network /path/to/densenet121.tgc	Download [`densenet121.tgc` from GitHub](https://github.com/seuretm/ocrd_typegroups_classifier/raw/master/ocrd_typegroups_classifier/models/densenet121.tgc)	ocrd-typegroups-classifier -I OCR-D-IMG -O OCR-D-IMG-FONTS

Notes on parameter usage

E.g.

• which parameters do you use with what values?
• which parameters are insufficiently documented?
• which aspects of a processor should be parameterizable but are not?

Notes on document-specific usage

E.g. which processors worked best with what material? -- feel free to post sample images here, too.