i2OCR is a free online Optical Character Recognition (OCR) web application that extracts text from images or scanned documents (PDF) so it can be edited, formatted, indexed, searched, or translated.
Text images could be a screenshot of a digital camera or photocopy of a scanned document such as books, faxes, receipts, bank statements, contracts, bills, business cards, mails, passport, and IDs.
i2OCR recognizes multi-column documents written in 100+ languages, supports several major input image formats and PDF, which can be loaded from disk or URL, displays recognized text as well as input source image side by side to facilitate reviewing mis-recognized words. Recognized text can be downloaded as Text file, MSWord doc, HTML file, simple PDF, or searchable PDF (PDF/A), translated, or edited online using Google Docs.
i2OCR respects your privacy and does not share your input or output files with third party. All input images and PDFs and generated text files are automatically deleted within a short period of time typically an hour. i2OCR offers unlimited uploads, no email or registration is required, and on top of that it is 100% free!
i2OCR is owned and operated by sciweavers.org