Testimonials


I have used many different Imaging products. Hands down you have the best product out of the bunch. I love the fact it is extendable - it works fast and it just works. Keep up the fantastic work.

Steve Thompson
Electrical Resources, Inc


VintaSoft OCR .NET Plug-in - History

Version 3.5 (version 8.5 of VintaSoft Imaging .NET SDK)

  • The used Tesseract OCR engine has been updated to version 3.04:
    • improved the quality of text recognition
    • extended the list of supported languages for recognition
  • Added the ability to use the Tesseract OCR engine in multithreaded environment.
  • Improved the quality of text recognition in color images.
  • Reduced the peak memory usage allocated during recognition of text in color images.
  • Added the ability to import/export the tree of recognition results to HOCR format.
  • Many minor fixes and improvements.


Version 3.4 (version 8.4 of VintaSoft Imaging .NET SDK)

  • Added the ability to specify the ortogonal rotation of text region before the text recognition. In previous versions all text was recognized as non-rotated.

Version 3.3 (version 8.3 of VintaSoft Imaging .NET SDK)

  • OCR Demo now can create searchable PDF documents with MRC compression.

Version 3.1 (version 8.1 of VintaSoft Imaging .NET SDK)

  • Some minor fixes.
  • Improved the code of Ocr Demo application.

Version 3.0 (version 8.0 of VintaSoft Imaging .NET SDK)

  • Assemblies were renamed and made changes in structure of namespaces. For more information click here.

Version 2.2 (version 7.2 of VintaSoft Imaging .NET SDK)

  • The used Tesseract OCR Engine upgraded to version 3.02:
    • Improved OCR quality.
    • New supported languages: Afrikaans, Albanian, Azerbaijani, Belarusian, Bengali, Estonian, Basque, Frankish, Galician, Croatian, Icelandic, Malayalam, Macedonian, Maltese, Malay, Swahili, Tamil, Telugu.
  • Some minor fixes.

Version 1.0 (version 6.0 of VintaSoft Imaging .NET SDK)

  • Base OCR .NET interface created (Vintasoft.Ocr.dll):
    • The ability to recognize text on image or image collection.
    • The ability to recognize text in the region of interest on image.
    • The ability to receive progress of recognition.
    • The ability to apply the image segmentation before starting of optical character recognition and set the recognition parameters for each image region.
    • The ability to obtain the recognition result in a hierarchy: Document, Page, Region, Paragraph, Line, Symbol.
    • The ability to browse through the recognition result.
    • The ability to edit the recognition result.
    • The ability to save the recognition result into a text (TXT) document.
  • Tesseract OCR interface created (Vintasoft.Ocr.Tesseract.dll):
    • Created interface provides access to Tesseract OCR engine.
    • The ability to recognize text the image.
    • The ability to recognize text in the region of interest on image.
    • Supported languages: Arabic, Bulgarian, Catalan, Czech, Сherokee, СhineseSimplified, ChineseTraditional, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Latvian, Lithuanian, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian, Slovakian, Slovenian, Spanish, Swedish, Tagalog, Thai, Turkish, Ukrainian, Vietnamese.
    • The ability to receive progress of recognition.
    • The ability to get/set Tesseract OCR variables.
    • The ability to use user-defined dictionaries.
  • Searchable PDF generation interface created (Vintasoft.Pdf.Ocr.dll):
    • The ability to save the recognition result into searchable PDF document as text.
    • The ability to save the recognition result into searchable PDF document as rasterized image and hidden text.