Difference between revisions of "Optical Character Recognition"

From ArchWiki
Jump to: navigation, search
(Splitted (tesseract разделили на несколько языковых пакетов).)
m (Layout analyzers and user interfaces: update URL)
(6 intermediate revisions by 3 users not shown)
Line 9: Line 9:
  
 
== OCR software ==
 
== OCR software ==
=== OCR (Optical Character Recognition) Engines ===
 
* {{App|[[CuneiForm]]|A command line OCR system originally developed and open sourced by Cognitive technologies. Supported languages: eng, ger, fra, rus, swe, spa, ita, ruseng, ukr, srp, hrv, pol, dan, por, dut, cze, rum, hun, bul, slo, lav, lit, est, tur.|https://launchpad.net/cuneiform-linux|{{Pkg|cuneiform}}}}
 
* {{App|[[GOCR]]/JOCR|An OCR engine which also supports barcode recognition.|http://jocr.sourceforge.net/|{{Pkg|gocr}}}}
 
* {{App|[[Ocrad]]|An OCR program based on a feature extraction method.|http://www.gnu.org/software/ocrad/|{{Pkg|ocrad}}}}
 
* {{App|[[Tesseract]]|"Probably one of the most accurate open source OCR engines available". Package splitted, you need install some datafiles for each language ({{Pkg|tesseract-data-eng}} for examle).|http://code.google.com/p/tesseract-ocr/|{{Pkg|tesseract}}}}
 
  
=== Layout analysers and user interfaces ===
+
=== OCR (Optical Character Recognition) engines ===
* {{App|[[OCRFeeder]]|Python GUI for Gnome which performs document analysis and rendition, and can use either [[CuneiForm]], [[GOCR]], [[Ocrad]] or [[Tesseract]] as OCR engines. It can import from PDF or image files, and export to HTML or OpenDocument. |http://live.gnome.org/OCRFeeder|{{pkg|ocrfeeder}}}}
+
 
* {{App|[[YAGF]]|graphical interface for the [[CuneiForm]] text recognition program on the Linux platform. Available from community repository|http://symmetrica.net/cuneiform-linux/yagf-en.html|{{Pkg|yagf}}}}
+
* {{App|CuneiForm|Command line OCR system originally developed and open sourced by Cognitive technologies. Supported languages: eng, ger, fra, rus, swe, spa, ita, ruseng, ukr, srp, hrv, pol, dan, por, dut, cze, rum, hun, bul, slo, lav, lit, est, tur.|https://launchpad.net/cuneiform-linux|{{Pkg|cuneiform}}}}
* {{App|[[gscan2pdf]]|scans, runs Tesseract and creates a PDF all in one go|http://gscan2pdf.sourceforge.net/|{{AUR|gscan2pdf}}}}
+
* {{App|GOCR/JOCR|OCR engine which also supports barcode recognition.|http://jocr.sourceforge.net/|{{Pkg|gocr}}}}
* {{App|[[OCRopus]]|OCR ''platform'', modules exist for document layout analysis, OCR engines (it can use Tesseract or its own engine), natural language modelling, etc. Available from [[AUR]]|http://code.google.com/p/ocropus/|{{AUR|ocropus}}}}
+
* {{App|Ocrad|OCR program based on a feature extraction method.|http://www.gnu.org/software/ocrad/|{{Pkg|ocrad}}}}
 +
* {{App|Tesseract|Accurate open source OCR engine. Package splitted, you need install some datafiles for each language ({{Pkg|tesseract-data-eng}} for example).|http://code.google.com/p/tesseract-ocr/|{{Pkg|tesseract}}}}
 +
 
 +
=== Layout analyzers and user interfaces ===
 +
 
 +
* {{App|gImageReader|Graphical GTK frontend to Tesseract.|http://gimagereader.sourceforge.net/|{{AUR|gimagereader}}}}
 +
* {{App|gscan2pdf|Scans, runs Tesseract and creates a PDF all in one go.|http://gscan2pdf.sourceforge.net/|{{AUR|gscan2pdf}}}}
 +
* {{App|OCRFeeder|Python GUI for Gnome which performs document analysis and rendition, and can use either CuneiForm, GOCR, Ocrad or Tesseract as OCR engines. It can import from PDF or image files, and export to HTML or OpenDocument.|http://wiki.gnome.org/OCRFeeder|{{Pkg|ocrfeeder}}}}
 +
* {{App|OCRopus|OCR ''platform'', modules exist for document layout analysis, OCR engines (it can use Tesseract or its own engine), natural language modeling, etc.|http://code.google.com/p/ocropus/|{{AUR|ocropus}}}}
 +
* {{App|[[YAGF]]|Graphical interface for the CuneiForm text recognition program on the Linux platform.|http://symmetrica.net/cuneiform-linux/yagf-en.html|{{Pkg|yagf}}}}

Revision as of 17:15, 29 August 2013

Tango-document-new.pngThis article is a stub.Tango-document-new.png

Notes: please use the first argument of the template to provide more detailed indications. (Discuss in Talk:Optical Character Recognition#)

There are several steps to the whole OCR process, the actual OCR engine is only part of this:

  1. scanning
  2. document layout analysis
  3. optical character recognition
  4. post-processing (formatting, PDF creation)

OCR software

OCR (Optical Character Recognition) engines

  • CuneiForm — Command line OCR system originally developed and open sourced by Cognitive technologies. Supported languages: eng, ger, fra, rus, swe, spa, ita, ruseng, ukr, srp, hrv, pol, dan, por, dut, cze, rum, hun, bul, slo, lav, lit, est, tur.
https://launchpad.net/cuneiform-linux || cuneiform
  • GOCR/JOCR — OCR engine which also supports barcode recognition.
http://jocr.sourceforge.net/ || gocr
  • Ocrad — OCR program based on a feature extraction method.
http://www.gnu.org/software/ocrad/ || ocrad
  • Tesseract — Accurate open source OCR engine. Package splitted, you need install some datafiles for each language (tesseract-data-eng for example).
http://code.google.com/p/tesseract-ocr/ || tesseract

Layout analyzers and user interfaces

  • gImageReader — Graphical GTK frontend to Tesseract.
http://gimagereader.sourceforge.net/ || gimagereaderAUR
  • gscan2pdf — Scans, runs Tesseract and creates a PDF all in one go.
http://gscan2pdf.sourceforge.net/ || gscan2pdfAUR
  • OCRFeeder — Python GUI for Gnome which performs document analysis and rendition, and can use either CuneiForm, GOCR, Ocrad or Tesseract as OCR engines. It can import from PDF or image files, and export to HTML or OpenDocument.
http://wiki.gnome.org/OCRFeeder || ocrfeeder
  • OCRopus — OCR platform, modules exist for document layout analysis, OCR engines (it can use Tesseract or its own engine), natural language modeling, etc.
http://code.google.com/p/ocropus/ || ocropusAUR
  • YAGF — Graphical interface for the CuneiForm text recognition program on the Linux platform.
http://symmetrica.net/cuneiform-linux/yagf-en.html || yagf