Fiche du document
22 février 2019
- doi: 10.58079/sj2j
info:eu-repo/semantics/openAccess
Sujets proches
Skills training Documents Documents, Legal Documents Public documents Official publications Government documents Baptismal fonts Documents Documents Indentures Documents Charters--Law and legislation Ethology Documents Manuscript repositories Manuscript depositories Manuscripts--Repositories Manuscripts--Depositories OCR (Optical character recognition)Citer ce document
Robert Nasarek, « Ocropy OCR - good results for Gothic/Fraktur Typeface », OoO, ID : 10.58079/sj2j
Métriques
Partage / Export
Résumé
Ocropy (also called ocropus) is not a standalone program for text recognition: it consists of several command line modules for binarization (creates a binary raster graphic) segmentation (splitting documents into lines) optical character recognition (OCR) controlling the recognised text and training new character sets. Ocropy is free, modules for new fonts are relatively easy to create, and - with a little preprocessing of the images - it has very good recognition rates - up to 98% (see fi...