Making sense of Indian documents

Accurate and fast digitization of Hindi, Marathi, Gujarati, Tamil, and Sanskrit

Our text recognition (OCR) programs convert printed Hindi, Marathi, Tamil, Gujarati, and Sanskrit texts into digital, editable text documents in Unicode format, either in Devanagari or in Tamil script. OCR ("optical character recognition") programs take scanned text images and transform them automatically into computer readable text files.
OCR programs are used successfully by data entry companies, publishing houses and universities - whenever large amounts of Hindi and Sanskrit text have to be digitized in short time and high quality.

ind.senz OCR programs or "Hindi scanners" achieve high accuracy rates on typical Devanagari fonts. Try the free demo versions with your data!

Download the PDF fact-sheet about ind.senz and its OCR engines.  
Download the PDF info-sheet about how ind.senz OCR programs work.  

HindiOCR SDK for software developers

Use our OCR SDK (software development kit) to build Hindi OCR support into your own Windows© applications!


January 5th, 2016: Gujarati OCR ( released

August 4th, 2015: Marathi OCR ( released

All news and additional content