Text and Font Style Recognition

• Perform OCR on a digital image, delivering the text in:
  • The appropriate Serif, Sans Serif, or Monospace font style
  • A font that is closest in form to the recognized font in normal, bold, italic, or bold italic
• Scaled over a wide range of font sizes

Language Recognition

• Recognize text in English, French, German, Italian, Spanish, Portuguese, Danish, Dutch, Swedish, Norwegian, Hungarian, Polish, and Finnish
• Recognize one language at a time
• Includes dictionaries for all supported languages
• Accepts and applies user-defined words in a custom dictionary

Text Correction Capability

• Identify characters recognized with low confidence
• Make corrections to text prior to outputting to the document
• Build text proofing and character replacement functions into applications

Auto Rotation

• Accepts input images in any orientation and automatically rotates 0, 90, 180, or 270 degrees
• Returns the amount of rotation applied
• Uses the text to determine orientation
• Highly optimized for speed

Image Binarization

• Create black and white images from 24 bit color and 8 bit grayscale image file formats, with image input and conversion support provided by ImagXpress Document
• Retain non-text color regions for reinsertion into the output document

Deskew

• Full-page deskew on images with up to 15 degrees of skew

Image Input

• OCR Xpress includes ImagXpress Document for image input (including TIFF, JPEG, JBIG2, and more)
• Input uncompressed in-memory image data

File Output Formats

• The output from OCR Xpress is a digital file containing unformatted text, formatted text, or formatted text plus image data, delivered in a variety of file formats. OCR Xpress Professional outputs all file types listed below, INCLUDING PDF. OCR Xpress Standard outputs all file types listed below, EXCEPT PDF.
• ASCII
  • ASCII with no line breaks
  • ASCII with line breaks
  • ASCII with smart formatting (positioned with spaces)
  • ASCII, comma-delimited (one line per field)
  • ASCII, tab-delimited
• Excel v2.x (compatible with later versions)
• HTML, with a sub-folder of the same name containing images
• PDF
  • PDF - Searchable Image (Original Image with Hidden Text), PDF version 1.4 file (Professional edition only)
  • PDF - Formatted Text and Graphics (Normal), PDF version 1.4 file (Professional edition only)
  • PDF - Image only, PDF version 1.4 file (Professional edition only)
• RTF - Used for import to Word, WordPerfect, etc.
• WordPerfect 5.0, WordPerfect 5.1
• All image-only file formats supported by ImagXpress

Segmentation

• Automatically or manually locate regions of the input image and identify them as either images (whose color can be preserved) or areas containing recognizable text
• Access various regions separately, or recombine into fully-formatted documents such as RTF or PDF files

Edition Descriptions
The Standard Edition is a full-featured full-page OCR toolkit that supports many different export formats. The Professional Edition adds support for exporting PDF formats.