OCR splits words with a dash in to separate words

I notice that in my OCR results (Omni professional), values like "194155-CA" and "CM-6734-US" are split in to individual words.

"194155-CA" -
OCR word values:
194155
-CA

"CM-6734-US" -
OCR word values:
CM
-6734
-US

Is there any setting or other option where the resulting OCR word will keep the entire value together?

Thank you.

Hi,

After looking through our documentation, it appears that there isn't a simple setting or property that enables the OmniPage OCR engine to keep words together.

I have tested with both OCR engines and while the OmniPage engine does separate the words, our LEAD engine does not do this and outputs your desired results.

However, if you wish to use the OmniPage engine, a workaround that you can perform would be to use the SetRecognizedCharacters() method after you've recognized the characters. You would need to write your own logic to determine when a hyphen occurs and and manually stitch the words together.

SetRecognizedCharacters() method:
https://www.leadtools.com/help/leadtools/v20/dh/fo/iocrpage-setrecognizedcharacters.html

A similar example of this can be seen on the page linked below. This example showcases capitalizing the first character in every word, however the process of find a hyphen and manipulating character data should be similar.

GetRecognizedCharacters() method with example code:
https://www.leadtools.com/help/leadtools/v20/dh/fo/iocrpage-getrecognizedcharacters.html

Thanks a bunch for the work around suggestions.