Knowledge Base

Article ID: 534 | Category: Recognition | Type: Tips & Tricks | Last Modified: 7/7/2016

Recognizing symbols that aren't included in the alphabet of a language


Can ABBYY FineReader recognize text that contains unusual symbols (pictograms, the © and ® symbols, etc.)?


ABBYY FineReader can be trained to recognize all Unicode symbols.
To recognize text with uncommon Unicode symbols, follow the instructions below.

  1. Create a new language and add all the necessary symbols to its alphabet. 
    • Start ABBYY FineReader.
    • Open the Tools menu and select Language Editor.
    • Click the New button.
    • Select the language of the text you need to recognize as the base language and click OK.
    • Click the ... button next to the Alphabet box.
    • Add all the necessary symbols to the alphabet of the new language and click OK.
    • Specify the name of the new language. Tweak the additional parameters of the new language if necessary.
    • When you've finished editing the language, click OK.
  2. Train ABBYY FineReader to recognize the new symbols.
    • Select the new language as the language of the current document.
    • Open the Tools menu and click Options.
    • Select the Read tab.
    • If you're using ABBYY FineReader 11, select the Use built-in and user patterns option, then select the Read with training option.
      If you're using an earlier version of ABBYY FineReader, select the Train user pattern option.
    • Click OK.
    • Click the Read button to begin recognizing the document and training ABBYY FineReader to recognize the new symbols.
1033 people think this is helpful.
Was this information helpful to you?