A Compact Error-Correction Method for OCR Mark Fields
Original Publication Date: 1998-May-01
Included in the Prior Art Database: 2005-Apr-04
Publishing Venue
IBM
Related People
Sumikawa, M: AUTHOR [+2]
Abstract
Disclosed is a method for compact error-correction in OCR mark fields. This method reduces area for visual check and enhances the user interface of mark fields correction in OCR by overlapping display of mark fields elements.
A Compact Error-Correction Method for OCR Mark Fields
Disclosed is a
method for compact error-correction in OCR
mark fields. This method reduces area
for visual check and enhances
the user interface of mark fields correction in OCR by overlapping
display of mark fields elements.
The elements for
correction of mark fields are following
three.
1.
Identification of item
2.
Actual image
3.
Recognition result
Identification
of item is explanation of mark field.
For
example "Male" or "Female".
Actual image is bit map image filled by
people. Recognition result is code data
obtained by OCR.
Conventional
methods of mark fields correction use three
lines for visual check. The first line
is used for identification
of item, the second line is used for actual image and the third line
is used for recognition result. See Fig.
1.
Our method
reduces the area for the visual check by
overlapping the three elements for correction of mark fields.
Following are three cases that reduce the area.
case 1.
Display an identification of item, actual image
and recognition result to one
line by overlapping
them. For example it shows identification of item,
"Male", in blue,
actual image, "x", in black and
recognition result as pink or yellow
background. See
Fig.2. This is the most compact case.
case 2.
Display an identificat...