OCR - Image Reader

What it does

OCR - Image Reader lets you drag a box around part of the current tab and turns any text inside it into editable text. It helps anyone who needs to copy words from images, scanned PDFs, slides or pages that block text selection.

Key features

• Adds a toolbar button that lets you select a region of the active tab for recognition
• Uses the Tesseract engine, which reads a wide range of languages and detects text orientation
• Offers a second engine that can keep headings, lists, tables and equations
• Shows a progress bar for each detection step while recognition runs
• Unloads its library from the page when you finish to avoid lasting resource use

Use cases

• Copying text out of a screenshot or image embedded in a page
• Extracting content from a PowerPoint slide or scanned PDF shown in the browser
• Grabbing text from a site that prevents normal selection

Getting started

Click the toolbar button, drag a selection around the area containing text, and wait for the recognized text to appear.

Good to know

Recognition runs in the browser without a server, but the first use downloads language training data, which can take a few minutes. Plain OCR does not keep formatting, and accuracy depends on image quality.