How to use the OCR tool
- Add a scan, photo or screenshot by dropping it into the box, choosing a file or pasting it.
- Select the language of the text. Turn on Enhance contrast for faint or grey scans and Join lines if you want paragraphs instead of line breaks.
- Click Run OCR and wait while the text is recognized.
- Review the text, edit it if needed, then copy it or download it as a .txt file.
Features
- Optical character recognition (OCR) for JPG, PNG, WebP, BMP and GIF images.
- 22 languages, including right-to-left languages such as Urdu and Arabic.
- Contrast enhancement for faint scans.
- Option to join broken lines into paragraphs.
- Word count and confidence score for every result.
What is OCR?
OCR stands for optical character recognition. It is the technology that finds letters and words in a picture and turns them into text a computer can edit, copy and search. It is used to digitize printed documents, receipts, books and screenshots.
Frequently Asked Questions
What is OCR used for?
OCR is used to turn printed pages, receipts, forms, book pages and screenshots into editable, searchable text.
Which languages does the OCR support?
The tool supports 22 languages, including English, Urdu, Hindi, Arabic, Bengali, Persian, Spanish, French, German, Chinese and Japanese.
Can this OCR read a PDF?
This tool reads images. To read a scanned PDF, save the page as an image first and upload that.
Does the OCR keep tables and layout?
No. It returns the text only. Columns and tables may need manual formatting.
Is my document private?
The recognition runs in your browser, so your image is not uploaded to our servers.