| OCRFeeder | |
|---|---|
 | |
 | |
| Developer | Joaquim Rocha (Igalia) |
| Initial release | March 2009; 16 years ago (2009-03) |
| Stable release | |
| Repository | |
| Written in | Python,PyGTK |
| Operating system | Linux,Unix-like |
| Available in | Interface:Czech,Danish,German,English,Spanish,French,Galician,Italian,Norwegian (bokmål),Portuguese,Romanian,Slovenian,Swedish,Chinese[2] Recognition: depends on OCR engine used |
| Type | Optical character recognition |
| License | GPL (free software) |
| Website | wiki |
OCRFeeder is anoptical character recognition suite forGNOME, which also supports virtually any command-line OCR engine, such asCuneiForm,GOCR,Ocrad andTesseract. It converts paper documents to digital document files and can serve to make them accessible to visually impaired users.
OCRFeeder isfree and open-source software subject to the terms of theGNU General Public License (GPL) version 3 or later. It is available forLinux and otherUnix-like operating systems.
OCRFeeder was started as amaster's thesis incomputer science by Joaquim Rocha,[3] who was later hired byIgalia, S.L. and continued development there.[4][5]
The first version was published in March 2009.[6] The OCRFeeder project was initially published and hosted onGoogle Code, temporarily usedGitorious[7] and now uses the GNOME infrastructure.[8] Since 5 April 2010 a software package is included in the official Debian repositories.[9]
Version 0.7 from July 30, 2010, brought image pre-processing features, 0.7.1 (November 8, 2010) enabled for scanner access from within OCRFeeder.
OCRFeeder has a simple graphical user interface that is designed to the GNOMEHuman Interface Guidelines.It performs aDocument Layout Analysis and transfers the layout to capable output formats. It searches for content areas, outlines them and guesses the content type (text or image) and processes text areas through the OCR back-end. It can use virtually any command-line OCR engine as back-end and features auto-detection and auto-configuration for all popular free engines. OCR back-ends may be either auto-configured, the necessary command line entered in a GUI dialogue or configured directly via aXML file. Scan image post-processing including de-skewing can be done.[10] All recognition results can be reviewed and edited before saving to the desired output format. Sessions can be saved and loaded. The suite also includes aspell checker.[11] OCRFeeder has built-in procedures for the post-processing of the raw OCR results returned by the OCR engine. It can remove remaining segmentation to printed lines of text, even with removal of hyphenation.
Although OCRFeeder is a GUI tool, it can also run incommand line mode (as ocrfeeder-cli), which may be a useful tool for automatic documentbatch processing.[12] In this mode OCRFeeder uses the default OCR engine, which the user can set in the application's preferences.[13][14]
The program is written inPython and uses theGTK+ library (usingPyGTK).[12]It acts as agraphicalfront-end for other existing tools. For example, it does not make actual character recognition itself, but uses external programs such as an “OCR engine” that is installed on the system. It can automatically detect and configureCuneiForm,GOCR,Ocrad andTesseract as backend OCR engines.[15] Scanners are accessed viaSANE. For post-processing of scanned images there is integration of the command-line tool “Unpaper”,[12] among other things.PDF files are processed usingGhostscript in the backend.
OCRFeeder can import data fromPDF orgraphic files. From 0.7.1a version it supports grabbing images directly from thescanner device.[11]
The results can be saved inHTML,OpenDocument,plain text[16] or PDF[17] file formats.hOCR file output is also planned.[3] Initial formatting can be done directly in the program.
| Core Applications | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Extras |
| ||||||||||||||||
| Components |
| ||||||||||||||||
| Community | |||||||||||||||||
| People | |||||||||||||||||
