OCR – Extract Text from Image
Upload any image and instantly extract the text it contains. Runs entirely in your browser — no server, no upload, no data shared.
Drop an image here or click to browse
JPG, PNG, WebP, GIF, BMP, TIFF supported
Your image is never uploaded. OCR runs entirely in your browser using Tesseract.js. No data ever leaves your device.
Frequently Asked Questions
What is OCR?
Optical Character Recognition (OCR) is a technology that reads text from images and converts it into machine-readable characters. It works by analysing the shapes and patterns of letters in a photo or scan and mapping them to the corresponding text. This tool uses Tesseract.js, a powerful open-source OCR engine, running entirely inside your browser.
Which image formats work best?
PNG and TIFF images generally give the best results because they are lossless formats — no compression artefacts blur the letter edges. JPEG works well for photos with printed text. For the cleanest extraction, use images with high contrast between text and background, a resolution of at least 150 DPI, and minimal noise or skew. Avoid heavily compressed or very small images.
How accurate is the extraction?
Accuracy depends on the image quality and language selected. For clear, well-lit printed text in English, accuracy is typically very high (95%+). Handwriting, stylised fonts, low-resolution scans, or images with complex backgrounds reduce accuracy. Selecting the correct language in the dropdown significantly improves results for non-English content. Always review the extracted text before use.