Searching Method for Black Marks in Optical Character Recognition Forms
Original Publication Date: 1996-Jun-01
Included in the Prior Art Database: 2005-Mar-31
Arima, T: AUTHOR [+2]
Disclosed is a program that detects black marks in Optical Character Recognition (OCR) forms fast and accurately.
Searching Method for Black Marks in Optical Character
Disclosed is a program that detects black marks in
Recognition (OCR) forms fast and accurately.
of black marks in OCR forms is to detect (1) the
form position in a scanned image, (2) form's skew ratio in the image,
and (3) image's shrink/expansion ratio. They are used for character
segmentation. The search of black marks generally spends much time
because it scans large image data. Images by facsimile are generally
skewed much more than those by scanners and shifting more widely.
This disclosure is effective to detect black marks fast and
o This search method scans only small image area by using narrow
strips. So it can find black marks fast.
o This method searches edges in the neighborhood of the corner of
black marks. So the detected corners are highly reliable even
the form image is skewed.
shows the process flow of this disclosure to
detect upper-right corner position of the top left black mark.
1. Mark position estimation
Estimate the mark position by calculating it based on the
information of a user definition table.
2. Rough search of mark's upper edge (Fig. 1)
Search white-to-black transition point downward in a vertical
strip. If no edge found, shift the zonary area horizontally