Hindi OCR

HindiOCR converts scanned Hindi texts into digital texts in Devanagari-Unicode encoding (read more about how OCR software works).

The OCRed digital Hindi texts can be stored as Unicode UTF-8 text, RTF (Rich Text Format), or as PDF files with text under image. You can open them with text editors such as OpenOffice or Microsoft Word®, and work with them as you would with a typed Hindi document.

Key features of Hindi OCR

• High recognition accuracy and speed
• Built-in classifiers for most Hindi letters and ligatures - no training necessary!
• Unicode output in Devanagari
• Hindi lexicon for improved recognition results
• Training option for unusual and rare Hindi fonts
• Processes standard image formats (bmp, jpg, png, tiff, gif).
• Works on Windows XP® and Windows 7®

You can export the recognized Hindi text in various formats:

• Unicode text
• Unicode-RTF - click here to see a sample of fully editable output text in RTF.

WHY GO FOR PROFESSIONAL

Professional ver. also provides a professional version of the OCR program for Hindi. Use the professional version of HindiOCR to digitize large amounts of scanned Hindi documents in short time.

Additional features of the professional version:

• Recognition speed about 20% higher than in the basic version
• Batch recognition: Import large numbers of scanned Hindi pages, and have them recognized "at one go".
• Directory processing: OCR a complete directory of scanned Hindi documents, and store the result in a single text or PDF file - without creating and managing batch files.
• Text-under-Image PDF: The professional version of Hindi OCR can convert images of Hindi text into searchable PDF files in which the recognized text is "hidden" under the original image. Just download this sample PDF and search for की or any other Hindi word!
• Batch export: Export the complete recognized text in one file (txt, rtf, pdf), or as single files in text format.