106
Technical information
u
With low-quality originals, sometimes a good-quality photocopy
can yield better OCR results. This may be true for documents
with low contrast or printed on thin paper. On the other hand,
poor-quality photocopies with stripes, blotches or uneven
brightness will usually give worse results.
u
Page images should be free of notes, lines, doodles or spots.
Anything in a text zone that is not a printed character slows
recognition. Exclude such marks from text zones, or enclose them
in Ignore-type zones or use the eraser in the Tools palette to delete
them from the image.
u
Check the glass, mirrors, and lenses in your scanner for dust,
smudges, or scratches. Clean if necessary.
u
If your only criteria is OCR accuracy, prefer black-and-white
scanning for good quality documents with crisp black text on a
white background. Choose grayscale scanning if you are scanning
pages with text on colored or shaded backgrounds, or for degraded
documents with low or varied contrast.
u
Adjust the brightness and contrast sliders in the Scanner panel of
the Preferences dialog box, or on the scanner’s own interface. Or
choose Auto-brightness, if available. Experiment with different
settings combinations to get the desired results. See how to
optimize brightness on page 79.
u
Text in page images should be reasonably clean and crisp.
Characters should be separated from each other and not blotched
together or overlapping. Characters distorted by marks or smudges
may be unrecognizable.
u
If you have influence over the styling used in documents you want
to recognize, avoid having underlines used. It is difficult to
recognize underlined text because the underline changes the shape
of descenders on the letters q, g, y, p, and j.
u
Check the image resolution by selecting Show Page Info from the
File menu. The ideal resolution for OCR is 300 dpi. Images with
200 to 250 dpi or more than 400 dpi are liable to yield lower
Summary of Contents for OMNIPAGE PRO X
Page 1: ......