file:///C|/VisioneerDoc/html/glossary.htm
character format
Font and style information applied to characters. Character
format information includes the font name and type size, as
attributes such as underline, bold, italic, or some combination
of these properties. Compare with
page format
.
character identification error
An incorrectly recognized bitmapped character. There are
two kinds of character identification errors—substitutions
and rejects. A character substitution occurs when a character
is incorrectly recognized as another. A reject character results
from the inability of the OCR application to interpret a
character image with sufficient confidence. In such cases,
recognition is not attempted and the character is flagged as
illegible. Compare with
layout analysis error
.
character image
An arrangement of bits that defines a character in a font.
character recognition
The OCR process in which bitmapped character images are
interpreted and translated into ASCII computer codes.
character style
See
type style
.
clipboard
In Windows applications, temporary storage for text that is
cut or copied from a document. Text saved in the clipboard
may be pasted back into the same or another document.
column information
Part of Pro OCR’s page format information. Column
information includes the location of the column on the page,
the width of the column, and its left and right margins.
compression
Electronic method for reducing the size of a file without
losing any information in the file. Compressed TIFF files
take up significantly less disk space than uncompressed files.
See also
TIFF
and
CCITT
.
confidence
In Pro OCR, a measure of the certainty of an unknown
character’s identity. Above a certain confidence level, a
character is automatically recognized. At lower confidence
levels, a character may either be recognized, but flagged as a
suspect character, or not recognized and flagged as an
illegible character.
file:///C|/VisioneerDoc/html/glossary.htm (4 of 22) [1/20/2003 4:21:13 PM]
