Ocrad
| Ocrad
|
|
|---|---|
|
|
| Basic data
|
|
| developer | Antonio Diaz Diaz |
| Current version |
0.26 ( March 31, 2017 ) |
| operating system | Unixoid (e.g. Linux , BSD ) |
| programming language | C ++ |
| License | GPL ( Free Software ) |
| www.gnu.org/software/ocrad | |
Ocrad is free text recognition software (OCR) for the Linux command line that has been developed by Antonio Diaz Diaz since 2003 as part of the GNU project .
It accepts raster graphics in Netpbm formats (PBM, PGM, PPM), can output 8-bit coded text as well as UTF-8 and offers automatic recognition of the page design. It's written in C ++ . It is based on feature recognition, i.e. the extraction of features of a character.
The program is distributed as free software also in the source code under the conditions of version 3 or higher of the GNU General Public License (GPL). It can be installed directly from the standard package sources for most of the popular Linux distributions .
There are various programs that can be used as a graphic front-end: The former KDE scan software Kooka or the desktop OCR suite OCRFeeder .
power
Compared to the similar GOCR , it has the advantage of page layout detection and has a reputation for generally delivering slightly better results. Thus, until Tesseract was released in 2005 (2006?), It was one of the best and most popular text recognition software in the fields of free software and Linux software, alongside GOCR.