Release Notes

• Updated Tesseract to version 4.0.0

This is the first official release of tesseract4java that comes with pre-built binaries for all major platforms (runnable with Oracle JRE 8).

Release Notes

• Image pre-processing using Sauvola or Otsu binarization methods
• Integrated Box Editor
• Glyph overview for advanced training including glyph feature visualization
• Recognition comparison view with display of detected word boxes, symbol boxes, line numbers, base lines, x-lines, blocks, paragraphs, and font features
• Evaluation view that can generate recognition reports using ocrevalUAtion
• Batch recognition with text, HTML and XML output