Image & PDF OCR
Extract text from images and scanned PDFs — browser-based OCR — Free, no login required, processed securely in your browser
📖 How to Use
1. Select Files
Drag and drop or click to select images (JPG, PNG, WebP, BMP, etc.) or scanned PDFs. Multiple files are supported.
2. Choose Language
Select the language of the text to recognise. Korean + English is the default; choosing a single language gives higher accuracy.
3. Extract Text
Click "Start OCR" and each image or PDF page will be processed. Real-time progress is shown.
4. Copy or Download
Copy the extracted text to the clipboard or download it as a TXT file.
❓ FAQ
Are my files sent to a server?
No. All processing happens entirely inside your browser. Images and PDFs are never transmitted to any server.
Why is the first run slow?
On first use, the recognition data for the selected language (a few MB) is downloaded. It is cached in your browser afterwards, so subsequent runs are much faster.
The recognition accuracy is low — what can I do?
OCR works best on high-resolution images with sharp, clear text. Blurry photos, handwriting, skewed text, and complex backgrounds reduce accuracy.
Does it work on scanned PDFs?
Yes. Each page of a scanned or image-based PDF is rendered as an image and then OCR is applied. For PDFs that already have a text layer, the "PDF Text Extraction" tool is faster and more accurate.
Can it recognise handwriting?
Neat handwriting may be partially recognised, but accuracy is generally much lower than for printed or typed text. OCR is optimised for printed text.