OmniDoc Document ExtractionOmniDoc Document Extraction / OCR for scanned documents, with structure
OCR for scanned documents, with structure
Scanned PDF files and images have no text you can copy. OmniDoc recognises the text first, then organises the headings, paragraphs and tables by layout and gives you editable Markdown and JSON.
Upload a scan to recogniseDesktop app: no page limitUp to 501 pages per PDF and no monthly cap; free jobs wait in a queue. For longer files or when you are in a hurry, the OmniDoc desktop app has no page limit and no queue.
How this differs from plain OCR
Plain OCR gives you text page by page. OmniDoc also analyses the layout after recognition: it separates headings from body text, rebuilds tables into rows and columns, removes headers and footers and joins the text in reading order.
It works with scanned PDF files and with PNG, JPG, WEBP and BMP images. Check the recognised text against the original, especially numbers and tables.
How it works
Upload the file
Sign in with an OmniDoc account and drop the file on the page.
Start the extraction
PDF files, scans and images go through layout analysis, text recognition and table recognition; Office files, e-books and web pages are parsed directly.
Download the result
Download a ZIP file with Markdown, JSON and the images. The job runs in the background, so you can close the page.
Files it suits
Scanned paper documents
Contracts, archives and book pages scanned to PDF.
Photos of documents
Notices, forms and handouts photographed with a phone.
PDF files without a text layer
PDF files that were printed and scanned, so their text cannot be copied.
Scans you want to translate
Recognise the text first, then translate the whole document with the free document translation.
Supported formats
| File | How it is processed |
|---|---|
| PDF, scanned PDF, PNG, JPG, WEBP and BMP images | Layout analysis, text recognition (OCR) and table recognition |
| Word documents, PowerPoint presentations, Excel sheets, CSV | The document structure is read directly |
| EPUB e-books, HTML pages | Chapters and body text are parsed |
| Markdown, TXT, SRT and ASS subtitles | Converted into the same Markdown and JSON |
The OmniDoc desktop app
The free desktop app for Windows, macOS and Linux opens, edits and saves files on your own computer.
10,000 pages, and typing still keeps up
Edit a document of more than 10,000 pages as easily as a short one: each keystroke is laid out in about 9 ms, and jumping to any page takes about 3 ms.
100% classic Office XML support
.docx, .xlsx and .pptx open and save natively and stay standard Office files; formulas, charts and pivot tables keep working.
China's new national-standard formats
Open and edit OFD (GB/T 33190) and convert it to and from PDF; GB/T 7714—2015 references, a GB/T 7713.1 thesis template and the official-document numbering 一、（一）1.（1）① are built in.
Questions
Can a recognised scan be translated?
Yes. Extract the text first, then use the free document translation. PDF files with a text layer can be translated directly.
Is handwriting recognised?
The recognition is made for printed text. Results for handwriting depend on the writing, so check them.
Do I need an account?
Yes. Sign in with an OmniDoc account; signing up is free. Only you can see the files you upload and their results.
What are the limits of the free version?
Up to 501 pages per PDF and no monthly cap; free jobs wait in a queue. For longer files or when you are in a hurry, the OmniDoc desktop app has no page limit and no queue.
Try it now
Up to 501 pages per PDF and no monthly cap; free jobs wait in a queue. For longer files or when you are in a hurry, the OmniDoc desktop app has no page limit and no queue.
Upload a scan to recogniseGet the desktop app