Our OCR program for Sanskrit converts printed Sanskrit texts into computer readable, editable and searchable digital documents in Unicode-Devanagari encoding. The recognized Sanskrit text can be stored in plain text, RTF or as searchable, text-under-image PDF files.
The program has been developed for the scientific community, but is also useful for publishing houses and private users studying Sanskrit.
SanskritOCR contains all features of the professional versions of ind.senz OCR engines. This includes batch processing, full directory OCR, and pdf output.
Starting with version 220.127.116.11, the Sanskrit OCR engine uses new methods for handling unknown Sanskrit words. Nevertheless, due to the complexity of Sanskrit, the accuracy rates and speed of the program are slightly lower than for our OCR for Hindi.