Public
- Public
- Network
- Groups
- Featured
- Popular
- People

Animated demo. The first page shows the heading: OCR PDFs and images directly in your browser This tool runs entirely in your browser. No files are uploaded to a server. Then a drop area labelled: "Drag and drop a PDF, JPG, PNG, or GIF file here or click to select a file" An image is dropped on it and gets OCRd. Then the drop zone is clicked, a PDF is selected and every page of that PDF is displayed as an image and then OCRd in turn.

Download link

Animated demo. The first page shows the heading: OCR PDFs and images directly in your browser This tool runs entirely in your browser. No files are uploaded to a server. Then a drop area labelled: "Drag and drop a PDF, JPG, PNG, or GIF file here or click to select a file" An image is dropped on it and gets OCRd. Then the drop zone is clicked, a PDF is selected and every page of that PDF is displayed as an image and then OCRd in turn.

Notices where this attachment appears

Embed this notice
Simon Willison (simon@fedi.simonwillison.net)'s status on Sunday, 31-Mar-2024 06:14:19 JST Simon Willison

I built a new tool: https://tools.simonwillison.net/ocr - it runs OCR against images and PDFs entirely in your browser (no file upload needed) using Tesseract.js and PDF.js
I wrote more about the tool and how I built it (with copious amounts of Claude 3 Opus and a little bit of ChatGPT) here: https://simonwillison.net/2024/Mar/30/ocr-pdfs-images/

In conversation about 11 months ago from fedi.simonwillison.net permalink