Operation Manual
32
Section 6: Using Training Mode
(This feature is not available for Asian languages)
If you are processing documents with a non standard font and you notice that Readiris is systematically
having trouble recognizing characters, use the Training Mode to train the recognition system on the fonts
and character shapes you are using.
During the training process, any characters the recognition system isn't sure of are displayed in a preview
window, in combination with the word in which they were spotted and the result suggested by Readiris.
1
A character Readiris isn't sure of.
2
The word in which the character
was spotted.
3
The solution how Readiris suggests
to recognize it.
Training can substantially enhance the accuracy of the recognition system and is particularly useful when
recognizing distorted, defaced forms. Training can also be used to train Readiris on special symbols it is
unable to recognize initially, such as mathematical and scientific symbols and dingbats.
ATTENTION: training occurs during recognition. The training results are temporarily stored in the
computer memory, for the duration of the recognition. Readiris will no longer display the trained characters
when OCRing the rest of the document. When a new document is OCRed, the training results are erased.
To save training results permanently, save them in a Training Results set. Once Training Results have been
saved, you can also use them without activating Training Mode.
When is it better not to use Training Mode?
When you are processing documents with a misleading or nearly unreadable content - such as a
picture showing an opened book or showing a user interface. In this case it is better to change the
Zone Type and set it to Graphic. This way you avoid Readiris trying to recognize those parts of the
document.
When you are processing documents that are too dark or to bright, it is better to Adjust the Image
Quality so that the characters are better isolated.
When processing Digital Camera Images the final result is often easier to improve by correcting
the lighting conditions, focus, camera stability and taking a new picture instead of trying to process
a low quality image.
When you want to inspect the recognized text and make necessary corrections, it is better to use
the Text Corrector instead of the Training Mode.