0

I am using tika parser and tika core 2.x dependencies and want to read the characters inside images. Is there anyway to achieve this using tika without using tesseract installation.

DeadPool
  • 40
  • 8
  • Use a different OCR engine? – Gagravarr Jan 25 '23 at 05:37
  • @Gagravarr, is there any doc i can refer to ? I think other OCR engines might be paid right. Not sure though. – DeadPool Jan 25 '23 at 16:31
  • Tesseract is free, available for basically all platforms, and works well. If you don't want to use it you presumably have a good reason and a chosen alternative? – Gagravarr Jan 26 '23 at 07:08
  • @Gagravarr The issue is during scanning the fancy texts. Tesseract is working fine for normal fonts but for fancy kind of fonts, scanning is not working. Is there any way we can implement for all kinds of fonts as well using tesseract only. – DeadPool Jan 26 '23 at 18:14

0 Answers0