(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 is not 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 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.
Go to Settings > Training Mode.
Select Training mode.
The option Start to create a new training
results set is now selected.
Click OK to close the
Training Mode settings for now.
The other options are explained in Combining
Training Mode with Training Results sets below.
At the end of the recognition, Readiris enters the Training
Mode.
The characters the recognition system is not sure of are displayed.

If the results are correct:
Click the Learn
button to save the result as sure.
The training results are temporarily stored in the computer
memory, for the duration of the recognition. When you scan
a new document, you will have to go through the same steps
again.
To avoid having to go through the same steps, you can combine
Training Mode with Training Results sets.
Click Finish to accept all solutions the software offers.
If the results are incorrect:
Type in the correct characters and click the Learn button.
Note:
if you are dealing with documents that contain special characters
that are not available on your keyboard, click the browse button
to open the Character Palette. Double-click the character you
want to insert.
You can also drag and drop a character from the Character Palette
to the character field in Training Mode.

or
Click Don't learn
to save the result as unsure.
Use this command for damaged characters which could be confused
with other characters if trained. E.g. the number 1 and the
letter I, which have an identical form in many fonts.
Click Delete
to delete characters from the output.
Use this button to prevent document noise from appearing in
the output file.
Click Undo to
correct mistakes.
Readiris keeps track of the last 32 operations.
Click Abort
to abort Training mode.
All training results will be deleted. Next time you process
a document, Training Mode will start again.
When Training Mode has finished, you can now save the Training Results sets.
As stated above, you can use the Training Mode combined with a Training Results set, in order to store the training results permanently. Using Training Results Sets is recommended when you are processing multiple documents that have the same typographic characteristics.
Go through Training Mode as explained above.
Return to Settings > Training Mode.
Click Save to save the Training Results set.
Name the Results set and save it in a location of your choice.
Note: Results sets are limited to 500 shapes. You are recommended to create separate sets for specific applications.

Now you have several possibilities:
You can select Start
to create a new training results set.
In this case a new Training Mode process starts.
You can select Add
to current training results set.
In this case the new Training results are only stored temporarily and
they are not stored in the Results set you saved.
You can click Select,
browse for the Results set you saved and select Start
to add to training results from <YourFileName.dict>.
In this case the new Training results are added to the Results set
you saved.
You can also choose to deactivate Training Mode and:
Don't use any training results.
Use
the current training results set.
In this case only the temporary training results are used and you don't
have to go through Training Mode again.
Click Select,
browse for the Results set you saved and select Use
training results from <YourFileName.dict>.
In this case you use the results from the stored Results set without
going through Training Mode.