• Home
• Download
• Usage
• Change Log
• Training
• Developers
• Book Digitization
• Resources/
  Links
• Feedback/
  Questions

VietOCR

Change Summary:

24 June 2024 - VietOCR v6.14.0 & VietOCR.NET v6.13.0

• Upgrade to Tesseract 5.4.1

7 June 2024 - VietOCR.NET v6.12.0

• Upgrade to Tesseract 5.4.0

16 March 2024 - VietOCR v6.13.1 & VietOCR.NET v6.11.1

• Support open multiple file selection
• Provide better visual indication of the current thumbnail

13 March 2024 - VietOCR v6.13.0 & VietOCR.NET v6.11.0

• Upgrade to Tesseract 5.3.4
• Implement open add image functionality using Shift key
• Adjust size and position of dialogs and components to accommodate long localized text
• Update translations

5 January 2024 - VietOCR v6.12.0 & VietOCR.NET v6.10.0

• Update to Leptonica 1.84.1

6 December 2023 - VietOCR v6.10.0 & VietOCR.NET v6.9.0

• Upgrade to Tesseract 5.3.3

29 July 2023 - VietOCR v6.9.0 & VietOCR.NET v6.8.0

• Upgrade to Tesseract 5.3.2

6 April 2023 - VietOCR v6.8.0 & VietOCR.NET v6.7.0

• Upgrade to Tesseract 5.3.1

27 December 2022 - VietOCR v6.6.0 & VietOCR.NET v6.5.0

• Upgrade to Tesseract 5.3.0

10 July 2022 - VietOCR v6.3.1 & VietOCR.NET v6.3.1

• Update translations

7 July 2022 - VietOCR v6.3.0 & VietOCR.NET v6.3.0

• Upgrade to Tesseract 5.2.0

5 March 2022 - VietOCR v6.2.0 & VietOCR.NET v6.2.0

• Upgrade to Tesseract 5.1.0

26 January 2022 - VietOCR v6.1.1

• Remove ghost4j and log4j due to vulnerabilities

11 January 2022 - VietOCR v6.1.0 & VietOCR.NET v6.1.0

• Upgrade to Tesseract 5.0.1

17 December 2021 - VietOCR v6.0 & VietOCR.NET v6.0

• Upgrade to Tesseract 5.0.0
• Update translations

28 November 2021 - VietOCR v5.8.0 & VietOCR.NET v5.8.0

• Upgrade to Tesseract 4.1.3 & Leptonica 1.82.0

18 October 2020 - VietOCR v5.7 & VietOCR.NET v5.7

• Support multiple renderers and provide pre- and post-processing for Bulk/Batch ops
• Various UI improvements

18 April 2020 - VietOCR v5.6.1 & VietOCR.NET v5.6.1

• Fix locked file issues with batch process

4 January 2020 - VietOCR v5.6 & VietOCR.NET v5.6

• Upgrade to Tesseract 4.1.1
• Fix Permission denied issue with GS 9.50

17 July 2019 - VietOCR v5.5 & VietOCR.NET v5.5

• Upgrade to Tesseract 4.1.0

30 October 2018 - VietOCR v5.4 & VietOCR.NET v5.4

• Upgrade to Tesseract 4.0.0

30 September 2018 - VietOCR v5.3 & VietOCR.NET v5.3

• Implement Find & Replace functionality

19 August 2018 - VietOCR.NET v5.2

• Upgrade to Tesseract 4.0.0-beta.4 (fd49206)
• Fix Save As function
• Fix Fit Image & Zoom In/Out function

11 August 2018 - VietOCR v5.2

• Upgrade to Tesseract 4.0.0-beta.4 (fd49206)

28 July 2018 - VietOCR v5.1.1

• Update Tess4J 4.1.1

22 July 2018 - VietOCR v5.1.0

• Upgrade to Tesseract 4.0.0-beta.3 (b502bbf) and language data
• Upgrade to Tess4J 4.1.0 and Lept4J 1.10.0
• Update dependencies

4 July 2018 - VietOCR.NET v5.1

• Upgrade Tesseract.NET (Tesseract 4.0.0-beta.3 b502bbf)

4 July 2018 - VietOCR.NET v4.7

• Update Tesseract.NET library to 3.3.0 (Tesseract 3.05.2 & Leptonica 1.75.3)

21 May 2018 - VietOCR.NET v5.0.3

• Fix Gridsplitter's resize issue

19 May 2018 - VietOCR v5.0.3 & VietOCR.NET v5.0.2

• Add support for Convert PDF to TIFF

10 May 2018 - VietOCR v5.0.2 & VietOCR.NET v5.0.1

• Update available language list to include scripts

3 May 2018 - VietOCR v5.0.1

• Update Tess4J 4.0.2 and Lept4J 1.9.4
• Update to current hunspell-1.6 on Linux

30 April 2018 - VietOCR.NET v5.0

• Rewrite using Windows Presentation Foundation (WPF)
• Upgrade Tesseract.NET (Tesseract 4.0.0-beta.1 45bb942)
• Upgrade Leptonica 1.75.3
• Upgrade Tesseract 4.00 fast language packs
• Autodeskew for batch and bulk processes
• Implement despeckle function

28 April 2018 - VietOCR v5.0

• Upgrade to Tesseract 4.0.0-beta.1 (45bb942) and language data
• Upgrade to Tess4J 4.0.0 and Lept4J 1.9.3
• Upgrade Tesseract 4.00 fast language packs
• Autodeskew for batch and bulk processes
• Implement despeckle function

16 April 2018 - VietOCR v4.7.2

• Update jai-imageio-core to 1.4.0 for Java 9 fixes
• Update to Tess4J 3.4.7 and Lept4J 1.6.4

25 March 2018 - VietOCR v4.7.1

• Update PDFBox dependencies

24 March 2018 - VietOCR v4.7

• Update to Tess4J 3.4.5; remove bundled Ghostscript DLL and use PDFBox if Ghostscript not available on system

22 February 2018 - VietOCR v4.6.3

• Update to Tess4J 3.4.4 and Lept4J 1.6.3

2 December 2017 - VietOCR.NET v4.5

• Update Tesseract.NET library (Leptonica 1.74.4)

14 November 2017 - VietOCR v4.6.2

• Update to Tess4J 3.4.2

16 October 2017 - VietOCR.NET v4.4

• Update Tesseract.NET library to 3.2.0-alpha4
• Update GhostScript to 9.22
• Add PDF output support for batch process

22 September 2017 - VietOCR v4.6.1

• Update Tesseract 3.05.01 (e2e79c4)
• Update to Tess4J 3.4.1

4 September 2017 - VietOCR v4.6

• Upgrade to Tesseract 3.05.01 (2158661)
• Upgrade to Tess4J 3.4.0

17 February 2017 - VietOCR v4.5

• Upgrade to Tesseract 3.05 (5afface)
• Upgrade to Tess4J 3.3.0

14 January 2017 - VietOCR.NET v4.3

• Update GhostScript to 9.20
• Update Tesseract.NET library to 3.2.0-alpha2
• Update to .NET Framework 4.5.2
• Additional image filters
• Port improvements made to Java version by John Helour, including:
  • Expand support to include Regex text replacements from DangAmbigs.txt file
  • Hyphen replacements

14 January 2017 - VietOCR v4.4

• Update GhostScript to 9.20
• Improvements by John Helour:
  • Additional image filters
  • Expand support to include Regex text replacements from DangAmbigs.txt file
  • Hyphen replacements

7 January 2017 - jTessBoxEditorFX v1.0

• jTessBoxEditor rewritten in JavaFX to address the existing issue of rendering complex scripts in Java Swing
• Upgrade Tesseract training executable 3.05dev (2016-11-11)
• Generated images are now compressed to reduce file size
• Additional parameters for text2image command
• Use BreakIterator for character boundary analysis

7 January 2017 - jTessBoxEditor v1.7.1

• Update Tesseract training executable 3.05dev (2016-11-11)

12 September 2016 - jTessBoxEditor v1.7

• Upgrade Tesseract training executable 3.05dev (2016-08-31)
• Generated images are now compressed to reduce file sizes
• Additional parameters for text2image command
• Use BreakIterator for character boundary analysis

4 June 2016 - jTessBoxEditor v1.6

• Upgrade Tesseract training executable 3.05dev (from https://github.com/UB-Mannheim/tesseract/wiki)
• Incorporate new training commands, including text2image (currently not usable on Windows)

30 May 2016 - VietOCR.NET v4.2

• Implement remove lines & crop image function
• Display segmented regions
• Update Tesseract.NET library
• Update GhostScript to 9.19

30 May 2016 - VietOCR v4.3

• Implement remove lines & crop image function
• Update Tess4J to 3.2.1
• Update various dependency versions
• Convert WIA scanned image BMP to PNG

20 February 2016 - VietOCR.NET v4.1

• Update Tesseract.NET to 3.0.2.0

30 January 2016 - VietOCR.NET v4.0

• Upgrade Tesseract.NET to 3.0.1.0 (Tesseract 3.04)
• Upgrade to .NET 4.0

18 January 2016 - VietOCR v4.1

• Upgrade to Tesseract 3.04 (953523b)
• Upgrade to Tess4J 3.0 and Lept4J 1.0.1
• Image zoom with mousewheel and Ctrl key
• Display segmented regions
• Update translations

12 December 2015 - VietOCR.NET v3.7

• Update Tesseract.NET to 2.4.1.0
• Update GhostScript to 9.18
• Fix a hang issue with download of multiple language data packs
• Image zoom with mousewheel and Ctrl key
• Update translations

2 May 2015 - jTessBoxEditor v1.4

• Incorporate improvements by A2K in using hotkeys for box movement control in Box View, and adjustable box scaling and margins of Box View

30 March 2015 - VietOCR v4.0

• Upgrade to Tesseract 3.03 RC (r1127)
• Upgrade Tess4J to v2.0
• Add support for searchable PDF output in bulk/batch mode

4 March 2015 - VietOCR v3.6 & VietOCR.NET v3.6

• Add Split TIFF function
• Add thumbnail bar for ease of page navigation
• Display useful info in statusbar
• Update links to OpenOffice dictionaries
• Add support for reading specific configs files for setting control parameters
• Java:
  • Update NHunspell to 1.2.5359
  • Update Tesseract.NET to 2.2.0.0
• .NET:
  • Update Hunspell to v1.3.3 and fix a NPE; add Windows 64-bit support
  • Update JNA to v4.1.0
  • Update Ghost4J to v0.5.1
  • Update Tess4J to v1.4.2

4 January 2015 - jTessBoxEditor v1.3

• Implement function to validate generated traineddata

19 November 2014 - jTessBoxEditor v1.2.1

• Fix a regression bug caused by RTL training by applying unicharset's Unicode character directionality fix only when RTL is selected

7 November 2014 - jTessBoxEditor v1.2

• Break up the training process to allow flexible, incremental training
• Incorporate logging

15 October 2014 - jTessBoxEditor v1.1

• Add training support for Right-to-Left (RTL) text
• Add horizontal box split using modifier keys
• Add split multi-page TIFF function

29 July 2014 - VietOCR v4.0 Beta

• Upgrade to Tesseract 3.03 RC (r1127)
• Upgrade Tess4J library
• Add support for searchable PDF output in bulk/batch mode

25 January 2014 - VietOCR v3.5 & VietOCR.NET v3.5

• Upgrade to Tesseract 3.02.03 (r866)
• Enhance Bulk ops with subdirectory support
• Incorporate image filters to enhance images for OCR
• Implement Auto Crop and Undo functions
• Additional translations
• Update Tess4J library; JNA to v4.0; JACOB to v1.17 (Java only)

16 November 2013 - jTessBoxEditor v1.0

• Integrate support for full automation of Tesseract training
• Bundle Tesseract Windows training executables (r866), English data, and config files
• Fix an issue with generated TIFF missing metadata
• Add an option to add noise to generated image
• Bug fixes and improvements

30 April 2013 - jTessBoxEditor v0.9

• Enhance Generate TIFF/Box functionality to allow for combining prepending symbols in addition to appending
• Fix a bug that failed to persist changes to table in edit mode
• Find function now supports partial matches
• Fix a problem with table not scrolling along when row header has focus and scrolling

16 April 2013 - jTessBoxEditor v0.8

• Add row number header
• Char cell now editable
• Convert Unicode escape sequences where possible
• Find box now displays Unicode characters and allows search using Unicode escape sequences
• Improve Generate TIFF/Box functionality:
  • automatically combine boxes that have the same coordinates or completely encloses one another
  • automatically combine boxes that are combining symbols, specified in an external file, with the main, base character
  • retain last-modified exp number in filename

6 January 2013 - VietOCR.NET v3.4

• Upgrade to Tesseract 3.02 .NET wrapper (r820) (https://github.com/charlesw/tesseract)
• Add hocr support for Bulk & Batch and command-line operations
• Update links to dictionary files

6 January 2013 - VietOCR v3.4.2

• Update Tesseract 3.02 to r820
• Add hocr support for Bulk & Batch and command-line operations
• Update links to dictionary files
• Update JNA to v3.5.1

28 November 2012 - VietOCR v3.4.1 & VietOCR.NET v3.3.1

• Add Bulk OCR process

3 November 2012 - VietOCR v3.4

• Upgrade Tesseract engine to v3.02 (r798)
• Enable text entry in the combobox for Tesseract 3.02's multi-language OCR support
• Fit Image now retains image aspect ratio
• Add optional support for using Tess4J library
• Update JACOB to 1.16.1 version

16 June 2012 - jTessBoxEditor v0.7

• Fix an issue with opening Help file on OS X
• For TIFF/Box generation:
  • increase line spacing
  • abbreviate bold/italic font style to b/i for filename
  • add a Prefix (Language Code) textbox
  • add support for text anti-aliasing

25 February 2012 - VietOCR v3.3 and VietOCR.NET v3.3

• Download Language Data will warn if the user does not have write access to tessdata folder
• Use icons from FatCow (http://www.fatcow.com/free-icons) and by Rimas Kudelis
• Fix a bug with scrollbars visible when Fit Image selected (Java only)
• Update Hunspell to v1.3.2 (Java only)

21 January 2012 - VietOCR v3.2.2

• Fix a context menu's font issue with displaying Unicode characters for spellcheck suggestions

14 January 2012 - VietOCR v3.2.1

• Fix an issue with opening Help file on OS X
• Update JACOB to 1.16-M2 version
• Update JNA to 3.4.0 version

26 November 2011 - VietOCR.NET v3.2

• Update Tesseract 3.01 to r639 (final release version)
• Remove unneeded liblept168.dll
• Update lists of language codes
• Add PSM support to execution from command line

22 October 2011 - VietOCR v3.2

• Update Tesseract 3.01 to r638 (final release version)
• Remove unneeded liblept168.dll
• Update lists of language codes
• Update JACOB to 1.16-M1 version
• Add PSM support to execution from command line

18 October 2011 - jTessBoxEditor v0.6

• Add a utility function that creates TIFF/Box pair suitable for training with Tesseract
• Fix a bug which may clear out a modified box file when loading another image
• Enhance box search operations
• Fix font issues in various visual components
• Merged box will have a character value composed of all the characters of the merging boxes

12 September - VietOCR.NET v3.1.1

• Fix a bug in which the arrow keys would scroll the picturebox even when the textbox has focus
• Provide Page Segmentation Mode options for Tesseract engine

12 September - VietOCR v3.1.5

• Update Tesseract 3.01 to r625
• Provide Page Segmentation Mode options for Tesseract engine

12 September 2011 - jTessBoxEditor v0.5.1

• Correct an issue with (small) image vertically centering in the image pane; align it to top of pane

5 September 2011 - jTessBoxEditor v0.5

• Display informational tooltip for boxed characters in image pane

14 August 2011 - VietOCR.NET v2.0.5

• Fix a bug in which the arrow keys would scroll the picturebox even when the textbox has focus

1 August 2011 - VietOCR.NET v3.1

• Integrate tesseractdotnet .NET wrapper DLL x86 (r48+) based on Tesseract 3.01 (r597)
• Remove tesseract.exe file
• Trap OutOfMemory exceptions that intermittently occur during drawing of selection boxes
• Refactor

1 August 2011 - VietOCR v3.1.4

• Update Tesseract 3.01 to r597

1 August 2011 - VietOCR.NET v2.0.4

• Trap OutOfMemory exceptions that intermittently occur during drawing of selection boxes
• Refactor

26 June 2011 - VietOCR.NET v3.00

• Use command-line process to invoke Tesseract 3.01 (r585) binary executable
• Include improved Vietnamese language pack

4 June 2011 - VietOCR v3.1.3

• Refactoring
• Improve program usability, enabling image nagivation and manipulation with keyboard
• Fix an EOL issue that broke Remove Line Breaks functionality on Windows
• Integrate Linux Sane scanning support
• Fix an issue with restart notification after language pack downloads
• Update Tesseract 3.01 to r585
• Replace Vietnamese language pack with an improved version

4 June 2011 - VietOCR v2.0.3 & VietOCR.NET v2.0.3

• Refactoring
• Improve program usability, enabling image nagivation and manipulation with keyboard
• Fix an installation issue that was unable to uninstall previous versions (.NET only)
• Fix an EOL issue that broke Remove Line Breaks functionality on Windows (Java only)
• Integrate Linux Sane scanning support

28 May 2011 - jTessBoxEditor v0.4

• Add a utility function for merging images into a multi-page TIFF

25 April 2011 - jTessBoxEditor v0.3

• Provide a close-up view of current box

14 April 2011 - jTessBoxEditor v0.2

• Add a provision to set font for the Box Coordinates table
• Set table row height to match font
• Incorporate a pangram into the Font dialog

10 April 2011 - jTessBoxEditor v0.1

• Support editing box data of both Tesseract 2.0x and 3.0x formats
• Implement box select & merge/split/insert/delete operations
• Implement box size change function via spinners
• Support Unicode conversion for the text field
• Include box search function

13 March 2011 - VietOCR v2.0.2/v3.1.2 & VietOCR.NET v2.0.2

• Incorporate deskew functionality using GMSE Deskew algorithm
• Fix a MissingResourceException associated with Font dialog (Java only)

6 March 2011 - VietOCR v2.0.1/v3.1.1 & VietOCR.NET v2.0.1

• Fix a bug which hangs the program if x.DangAmbigs.txt contains entries starting with an equal symbol
• Improve postprocessing performance by caching the word list used; reload only if changes
• Fix a bug that crashes the program when inline spellcheck suggests on empty text (.NET only)
• Incorporate Apple Java Extensions (Java only)

6 February 2011 - VietOCR v3.1

• Port changes from version 2.0
• Update Tesseract OCR engine to 3.01 (r551)

6 February 2011 - VietOCR v2.0 & VietOCR.NET v2.0

• Upgrade JACOB library to version 1.15-M4 (Java only)
• Add support for spellcheck suggestion in context menu
• Improve program accessibility and usability
• Add support for downloading and installing language data packs and appropriate spell dictionaries
• Add UI localization for Lithuanian and Slovak
• Refactor by breaking up large classes into smaller ones

11 November 2010 - VietOCR.NET v1.9

• Integrate Hunspell library to provide spellchecking and spellcheck-as-you-type functionality. Include English and Vietnamese dictionaries
• Add support for a custom dictionary
• List in correct order files generated from PDF conversion

3 October 2010 - VietOCR v3.0

• Upgrade Tesseract OCR engine to 3.0
• Replace old format (2.0x) language data with new format (3.0) language data
• Change datafile suffix from .inttemp to .traineddata

2 October 2010 - VietOCR v1.9

• Integrate a Java binding for Hunspell library to provide spellchecking and spellcheck-as-you-type functionality. Include English and Vietnamese dictionaries
• Add support for a custom dictionary
• List in correct order files generated from PDF conversion
• Upgrade JACOB library to version 1.15-M3
• Preset Tesseract path on Linux to /usr/bin, the default install location of Tesseract

6 September 2010 - VietOCR v1.8 & VietOCR.NET v1.8

• Display image information
• Add Screenshot Mode, which rescales low-resolution images to 300 DPI to be more suitable for OCR operations
• Read output and error streams to prevent subprocess to block or deadlock due to limited buffer size for standard output streams (Java version)
• Fix a problem in which paste (image) event fires twice (Java version)
• Fix an issue with subimages generated by selection box on Linux (Java version)

14 April 2010 - VietOCR v1.7 & VietOCR.NET v1.7

• Add provision to load UTF-8 text file into textbox
• Add Recent Files submenu
• Add Save button on toolbar
• Fix scale factor, offset issues in image manipulation
• Improve postprocessing for Vietnamese
• Add support for more VNI fonts to Vietnamese language data

30 January 2010 - VietOCR v1.6 & VietOCR.NET v1.6

• Fix an image size issue and associated scale factor when toggling between Fit Image vs. Actual Size after (Java) resizing window or (.NET) scrolling in picturebox
• Add unit test
• Improve post-OCR correction for Vietnamese
• Bundle Vietnamese language data for VNI & TCVN3 (ABC) fonts

21 December 2009 - VietOCR v1.5 & VietOCR.NET v1.5

• Add support for execution from command line
• Add support for paste image from clipboard
• Add support for JPEG2000 and PNM image types (Java version)

24 October 2009 - VietOCR v1.4 & VietOCR.NET v1.4

• Publish OCR interim results to produce more responsive UI performance, improving user experience
• Support for cancellation of running OCR tasks
• Merge PDF functionality

3 October 2009 - VietOCR v1.3 & VietOCR.NET v1.3

• Improve exception handling with appropriate error messages
• Improve handling of PDF documents that has many pages. Putting too many images, as a result of PDF extraction, in a multi-page TIFF eventually will generate out-of-memory exceptions
• Split PDF functionality

10 September 2009 - VietOCR v1.2 & VietOCR.NET v1.2

• Integrate PDF support using GPL Ghostscript

6 September 2009 - VietOCR v1.1 & VietOCR.NET v1.1

• Merge TIFF functionality

1 August 2009 - VietOCR.NET v1.0

• Update to Tessnet2 .NET wrapper for Tesseract 2.04 OCR engine
• Add more language codes to ISO639-3.xml file
• Fix a long-standing issue with accessing original image from a different thread; it would throw an InvalidOperationException with message "Object is currently in use elsewhere"
• Add support for custom text replacement in postprocessing

1 August 2009 - VietOCR v1.0.1

• Refactor for improvements

18 July 2009 - VietOCR v1.0

• Update to Tesseract 2.04 engine (bundled Windows executable)
• Add more language codes to ISO639-3.xml file
• Add a pangram.xml file for displaying appropriate Preview text in the Font Dialog for the OCR language currently selected
• Move various settings to the Options dialog
• Remove the option of Locating Tesseract on Windows. Current Tesseract is the executable bundled inside the program
• Add support for custom text replacement in postprocessing

21 June 2009 - VietOCR v0.9.13 & VietOCR.NET v0.9.4

• Update to Tesseract 2.04RC engine
• Add indeterminate progressbar for (more animated) task status
• Add All Image Files filter
• Remove Vietnamese-glyph font filter to now show all system fonts (Java version only)
• Change FontDialog's default Preview text to the standard English pangram to make it more universal (Java version only)
• Modify SimpleFilter to accept multiple file extensions (Java version only)

25 April 2009 - VietOCR v0.9.12

• Fix the way TESSDATA_PREFIX environment variable handled in Linux
• Clean up temporary files if errors occur during OCR operations
• Fix a regression EOL bug with output files in Windows
• Display appropriate error message during batch process

25 April 2009 - VietOCR.NET v0.9.3

• Refactor
• Display appropriate error message during batch process

15 March 2009 - VietOCR v0.9.11 & VietOCR.NET v0.9.2

• Add text formatting functionality

18 January 2009 - VietOCR v0.9.10 & VietOCR.NET v0.9.1

• Add watch folder functionality for Batch Processing support

10 January 2009 - VietOCR v0.9.9 & VietOCR.NET v0.9

• Revamp localization codes
• Add rudimentary support for English postprocessing

30 November 2008 - VietOCR v0.9.8 & VietOCR.NET v0.8

• Minor fixes and various improvements

10 November 2008 - VietOCR v0.9.7 & VietOCR.NET v0.7

• Implement image rotation functionality

2 November 2008 - VietOCR v0.9.6

• Fix an error with path in Linux
• Additional instruction for configuring Tesseract on Linux

28 October 2008 - VietOCR v0.9.5 & VietOCR.NET v0.6

• Integrate scanning support via WIA Automation Library v2.0

21 October 2008 - VietOCR v0.9.4 & VietOCR.NET v0.5

• Localize user interface

1 August 2008 - VietOCR.NET v0.4.2

• Add file drag-n-drop support
• Add selection rectangle
• Make Picturebox scrollable with mouse wheel
• Replace RTF-based help form with HTML-based

10 June 2008 - VietOCR.NET v0.2

• Integrate Tessnet2 .NET wrapper for Tesseract 2.03 OCR engine
• Use Vietnamese language data for Tesseract 2.03 (data for 2.01 crashes frequently with Tesseract 2.03)
• Add Vietnamese input methods
• Add post-processing for Vietnamese language

26 April 2008 - VietOCR v0.9.3 (aka, jtOCR)

• Proof-of-concept design
• Support TIFF image formats
• Add support for JPEG, GIF, BMP, PNG formats
• Add post-processing for Vietnamese to improve accuracy
• Add Vietnamese input methods
• Add recognition of selected area on image
• Add file drag-drop
• Add a context menu for the textarea
• Add support for selection of Look and Feel
• Display appropriate message when Tesseract engine crashes
• Fix the issue involving filepaths containing spaces
• Bundle JAI Image I/O 1.1 library
• Use Java 6.0
• Use Tesseract 2.03 OCR engine
• Use Vietnamese language data for Tesseract 2.03 (data for 2.01 crashes frequently with Tesseract 2.03)