OCR settings

OCR settings part of the Preferences dialog is used to set IMiS/OCR Server default recognition settings. These are used by IMiS/OCR Server defined jobs that inherit default OCR settings. General section consists of the following settings:

Language: select one or more recognition languages. Language setting is crucial for OCR process as certain characters which are not found among valid language character set are unrecognized or substituted by wrong characters. Language set in preferences can be overridden by job language and by user OCR request (default: English).

	Add selected available language(s) to the selected language list
	Remove selected language from the selected language list
	Remove all selected languages from the selected language list

Text type: used to set default input file text type/mode. Administrator can choose between numerous text types. Set this parameter if you're certain what kind of input requests will IMiS/OCR Server receive or leave Autodetect for OCR Engine to determine which recognition algorithm should be used (default: Normal).
Options:

Normal: this value corresponds to a common typographic type of text.
Typewriter: this value tells OCR Engine to presume that the text on the recognized image is typed on a typewriter.
Matrix: this value tells OCR Engine to presume that the text on the recognized image is printed on a dot matrix printer.
Index: this constant corresponds to a special set of characters including only digits written in ZIP-code style. They look as follows:
Handprinted: this value corresponds to handprinted text. It may look as follows:
OCR-A: this value corresponds to a monospaced font, designed for Optical Character Recognition. Largely used by banks, credit card companies and similar businesses. It may look as follows:
OCR-B: this value corresponds to a font designed for Optical Character Recognition. It may look as follows:
MICR-E13B: this value corresponds to a special set of numeric characters printed with special magnetic inks. MICR (Magnetic Ink Character Recognition) characters are found in a variety of places, including personal checks. It may look as follows:
MICR-CMC7: this value corresponds to a special MICR barcode font (CMC-7). It may look as follows:
Gothic: this value tells OCR Engine to presume that the text on the recognized image is printed with the Gothic type. It may look as follows:

Uncertain characters: use this parameter to set error highlighting level for uncertain characters. What this means is that IMiS/OCR Server depending on this setting marks characters for which OCR Engine is uncertain if they are correctly recognized. The level of sensitivity is set by this parameter (default: None).
Options:

None: the engine does not mark suspicious characters
Scanty: only those characters are highlighted which haven't been recognized or whose recognition is highly uncertain
Standard: same as "Scanty" but also highlights words which haven't been found in the dictionary
Thorough: same as "Standard" but also highlights characters which have been recognized slightly uncertainly

See the following subchapters for details on other OCR Settings sections:

	3.2.1.2.1 Preprocessing
	3.2.1.2.2 Barcodes
	3.2.1.2.3 Output formats

| Back | Main view | Parent doc