RecognizeIDCard fails to recognize Balkan ID card and omits diacritics

Aspose.OCR Product Family
1

Aspose.OCR for Java does not correctly recognize a Bosnia and Herzegovina identity card.

When the specialized RecognizeIDCard method is used, it does not return usable text from the attached ID card image.

When the same image is processed using the general Recognize method, most of the text is extracted. However, Bosnian/Croatian Latin characters with diacritics, such as Č , Ć , Ž , Š , Đ , č , ć , ž , š , and đ , are missing, incorrectly recognized, or replaced with basic Latin characters.

The issue remains reproducible when:

  • Language.Bos is explicitly selected.
  • Language.Hbs or Language.ExtLatin is used.
  • All Bosnian diacritic characters are explicitly included through setAllowedCharacters .
  • The result is saved directly to a UTF-8 text file, ruling out a console encoding problem.

Actual result

  • RecognizeIDCard does not correctly recognize the BiH identity card.
  • Recognize extracts some text but does not preserve the required Bosnian diacritics.

Expected result

RecognizeIDCard should recognize text from a Bosnia and Herzegovina identity card, and both recognition methods should correctly return all Latin characters with Bosnian diacritics.
kovacevic.jpg (53.1 KB)

2

Hi,

Could you please advise how to use it?

Thanks!

3

@KololoCoding
We have opened the following new ticket(s) in our internal issue tracking system and will deliver their fixes according to the terms mentioned in Free Support Policies.

Issue ID(s): OCRNET-1254

You can obtain Paid Support Services if you need support on a priority basis, along with the direct access to our Paid Support management team.