What is OCR - Image Reader?

OCR - Image Reader is a browser extension that adds a toolbar button to your browser. When clicked, it allows you to select a region on the screen, captures that area, and uses an internal OCR engine to recognize and extract text from the image. It supports over 100 languages and can handle various content types including images, PDFs, and PowerPoint slides.

How to use OCR - Image Reader?

Install the extension from the Chrome Web Store. Click the toolbar button, then select a region on your screen. The extension captures the area and performs OCR, displaying the extracted text. On first run, it may take a few minutes to fetch language training data, but subsequent uses are fast. You can also modify the image and drop it into the interface to retry if extraction is inaccurate.

Core features of OCR - Image Reader

Capture any screen region and extract text using OCR
Supports over 100 languages with automatic text orientation and script detection
Two engines: Tesseract for plain text and IBM Granite-Docling for formatting (headings, lists, styles, tables, equations)
Offline processing with no server-side interaction
Progress bar for each detection module
Automatic image inversion retry for low-confidence extractions (useful for dark themes)
Ability to modify and re-drop images for retry
No long-term resource usage; JS library loaded on demand