Comparison of optical character recognition software

This comparison of optical character recognition software includes:

  • OCR engines, that do the actual character identification
  • Layout analysis software, that divide scanned documents into zones suitable for OCR
  • Graphical interfaces to one or more OCR engines
  • Software development kits that are used to add OCR capabilities to other software (e.g. forms processing applications, document imaging management systems, e-discovery systems, records management solutions)
Sortable table
Name Founded year Latest stable version Release year License Online Windows Mac OS X Linux BSD Android iOS Programming language SDK? Languages Fonts Output Formats Notes
Google Drive OCR or Google Cloud Vision2015ProprietaryYesBrowserBrowserBrowserUnknown ? ?UnknownYes200+All fontstextGoogle blog post [1] [2]
Tesseract19854.1.12019ApacheNoYesYesYesYes ? ?C++, CYes100+[3]Any printed fontText, ALTO, hOCR,[4] PDF, others with different user interfaces[5] or the APICreated by Hewlett-Packard; under further development by Google[6]
ABBYY FineReader1989152019ProprietaryYesYesYesYesYes ? ?C/C++Yes192[7]All fontsDOC, DOCX, XLS, XLSX, PPTX, RTF, PDF, HTML, CSV, TXT, ODT, DjVu, EPUB, FB2[8]ABBYY also supplies SDKs for embedded and mobile devices. Professional, Corporate and Site License Editions for Windows, Express Edition for Mac.[9]
E-aksharayan 2010 Yes No Yes No ? ? 14 RTF, TXT, BRL
Asprise OCR SDK1998152015ProprietaryYesYesYesYesYes ? ?Java, C#,VB.NET, C/C++/DelphiYes20+[10]?Plain text, searchable PDF, XML[11]Java, C#, VB.NET, C/C++/Delphi SDKs for OCR and Barcode recognition on Windows, Linux, Mac OS X and Unix.[12]
AnyDoc Software1989??ProprietaryNoYesNoNoNo ? ?VBScript???Works with structured, semi-structured, and unstructured documents.
ConPDS OCR Engine[13]20142020.122020ProprietaryNoYesNoYesNo Yes YesC/C++No, Plug-n-Play?BIC (ISO 6346 standard) and ILU (EN 13044-1 standard) supported fontsJSONConPDS supplies custom trained OCR engine for the shipping and transportation industry. Supported by following programming languages: C/C++, C#, VB.NET, Java, and more on request.
CuneiForm19961.12011-04-19BSD variantNoYesYesYesYes ? ?C/C++Yes28Any printed fontHTML, hOCR, native, RTF, TeX, TXT[14]Enterprise-class system, can save text formatting and recognizes complicated tables of any structure
Dynamsoft OCR SDK20038.22012ProprietaryYesYesNoNoNo ? ?C/C++Yes40+[15]?PDF, TXT
OmniPage1970s19.22015ProprietaryYesYesYesYesNo ? ?C/C++, C#[16]Yes125[17]Machine and handprinted fontsDOC/DOCX XLS/XLSX PPTX RTF PDF PDF/A Searchable PDF HTML Text XML ePUB MP3Product of Nuance Communications
Microsoft Office OneNote 20072011?2007ProprietaryNoYesNoNoNo ? ?????
GOCR20000.52[18]2018-10-15GPLYes[19]YesYesYesYes ? ?C?20+?
Ocrad?0.26[20]2017-03-31GPLYesNoYesYesYes ? ?C++YesLatin alphabet?Command line
SmartScore199110.5.82015-07ProprietaryNoYesYesNoNo ? ?????For musical scores
Microsoft Office Document Imaging?Office 20072007ProprietaryNoYesNoNoNo ? ?????Uses OmniPage
Puma.NET??2009-10-29BSDNoYesNoNoNo ? ?C#Yes28Any printed font.NET OCR SDK based on Cognitive Technologies' CuneiForm recognition engine. Wraps Puma COM server and provides simplified API for .NET applications
ReadSoft???ProprietaryNoYesNoNoNo ? ?????Scan, capture and classify business documents such as invoices, forms and purchase orders integrated with business processes.
Scantron???ProprietaryNoYesNoNoNo ? ?????For working with localized interfaces, corresponding language support is required.
OCRFeeder2009-030.8.12014-12-22GPLNoNoNoYesNo ? ?Python???Features a full user interface and has a command-line tool for automatic operations. Has its own segmentation algorithm but uses system-wide OCR engines like Tesseract or Ocrad
OCRopus20071.3.32017-12-16ApacheNoNoYesYesYes ? ?Python?All languages using Latin script (other languages can be trained)Normal Latin script and Fraktur (other scripts can be trained)TXT, hOCR,[21] PDF[22]Pluggable framework under active development, used for Google Books
Name Founded year Latest stable version Release year License Online Windows Mac OS X Linux BSD Android iOS Programming language SDK? Languages Fonts Output Formats Notes

Evaluation

An analysis of the accuracy and reliability of the OCR packages Google Docs OCR, Tesseract, ABBYY FineReader, and Transym, employing a dataset including 1227 images from 15 different categories concluded Google Docs OCR and ABBYY to be performing better than others.[23]

References

  1. Dmitriy Genzel; Ashok Popat (May 6, 2015). "Paper to Digital in 200+ languages".
  2. Ashok Popat (Sep 4, 2015). "IEEE SPS: Optical Character Recognition for Most of the World's Languages".
  3. Based on count of language training files for version 3.04. Available at the download page.
  4. Usage explained in the Tesseract Readme and FAQ
  5. Such as ODF with OCRFeeder
  6. "GitHub - tesseract-ocr/tesseract: Tesseract Open Source OCR Engine (main repository)". Retrieved 2018-11-05.
  7. "ABBYY FineReader 14: Technical Specifications". Finereader.abbyy.com. Retrieved 2017-02-23.
  8. "ABBYY FineReader 11: Technical Specifications". Finereader.abbyy.com. Retrieved 2013-09-12.
  9. "Top OCR Software". Ocrworld.com. 2010-03-30. Archived from the original on 2017-02-23. Retrieved 2013-09-12.
  10. "Asprise OCR SDK Features". asprise.com. Retrieved 2014-06-21.
  11. "Asprise Java OCR Library Features". asprise.com. Retrieved 2014-06-21.
  12. "Asprise Java, C#/VB.NET OCR API". asprise.com. 2015-11-19. Retrieved 2015-11-19.
  13. "ConPDS Homepage".
  14. Debian manual page for Cuneiform for Linux version 1.1.0
  15. "OCR SDK Language Packages Download". Dynamsoft.com. Retrieved 2013-09-12.
  16. "OmniPage CSDK - OCR Document Capture Toolkit | Document Imaging & OCR". Nuance. Archived from the original on 2010-08-24. Retrieved 2013-09-12.
  17. "OmniPage Standard Document Conversion". Nuance. Archived from the original on 2014-03-13. Retrieved 2014-02-25.
  18. "GOCR Homepage". wasd.urz.uni-magdeburg.de. Retrieved 2018-10-17.
  19. "GOCR". Jocr.sourceforge.net. Retrieved 2013-09-12.
  20. Diaz, Antonio (2015-04-16). "GNU Ocrad 0.26 released" (Mailing list). info-gnu.
  21. OCRopus includes the ocropus-hocr tool which produces hOCR from the recognition results.
  22. In combination with the hocr-tools
  23. Assefi, Mehdi (2016-12-01). "OCR as a Service: An Experimental Evaluation of Google Docs OCR, Tesseract, ABBYY FineReader, and Transym". ResearchGate. Retrieved 2019-01-31.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.