The following table lists the features of the OCR module:
Feature Details
Supported
languages
• English
• Danish
• Dutch
• Finnish
• French
• German
• Italian
• Norwegian
• Polish
• Portuguese
• Russian
• Spanish
• Swedish
Dictionaries Each language has one associated dictionary. The search order of language dictionaries can be
configured in a script.
Supported text
types
• Common typographic (serif, sans‑serif, italic, monospace)
• Typewriter‑printed
• Dot‑matrix‑printed
• ZIP‑code‑style numerals
• Hand‑printed text (best performance when in a comb or frame)
• OCR‑A
• OCR‑B
• MICR (E‑13B and CMC‑7)
• Gothic
Supported input
text size
10 points–220 points
Default output fonts The following selections are made for default output fonts based on the input font:
• Serif fonts—Times New Roman
• Sans‑serif fonts—Arial
• Monospaced fonts—Courier New
Output fonts can be changed to any other TrueType font installed on the system within a script, after
the OCR operation, and before the text is exported to a document.
Zoning
• Automatic—The entire page is scanned and analyzed for blocks of text.
• Manual—The script defines regions on a page for OCR scanning. This method is faster, since it
does not require analyzing the entire page.
Available output
formats
• HTML
• Searchable PDF
• Plain text (TXT)
• Rich Text Format (RTF)
Developing workflow solutions 47
To Next Page
