Cuneiform
Cuneiform is a multi-language, open source optical character
recognition system originally developed by Cognitive Technologies. This
software package also performs layout analysis and text format
recognition. CuneiForm for Linux does not have a graphical interface
component, but graphical user interfaces have been developed.
CuneiForm preserves the structure of the document and its
formatting. The program recognizes the table of any structure and
complexity, including without displaying the lines of the grid.
The results of the program can be edited in Office
applications, text editors, and save in popular formats, to conduct
full-text searches.
Features include:
- Uses the OmniFont system
- Recognized by any printed fonts: books, newspapers,
magazines, prints from the laser and dot matrix printers, typewriters,
texts
- Recognition mode optimized for text printed with a dot
matrix printer
- Recognition mode optimized for text that has been faxed in
200x100 DPI
- Output formats: HTML, hocr (hOCR HTML format), Native
(Cuneiform's own format), rtf, smarttext, and text
- To improve the quality of
recognition, Cuneiform performs a dictionary check
- Internationalization support: Bulgarian, Czech, Danish
Dutch, English, Estonian, French, German, Croatian, Hungarin, Italian,
Latvian, Lithuanian, Polish, Portugese, Romanian, Russian,
Slovenian, Spanish, Serbian, Swedish, Turkish, and Ukrainian
Return
to OCR Tools Home Page
Last Updated Friday, April 26 2013 @ 08:13 AM EDT
|
