OCR tiếng Việt

Make a PDF searchable and copyable.

How it works:

Extract Text: Uses Tesseract OCR to recognize text from scanned images or PDFs.
Searchable Output: Creates a new PDF with an invisible text layer, making your document fully searchable while preserving the original appearance.
Character Filtering: Use whitelists to filter out unwanted characters and improve accuracy for specific document types (invoices, forms, etc.).
Multi-language Support: Select multiple languages for documents containing mixed language content.

Click to select PDF or drag and drop

Your files never leave your device.

Languages in Document

Selected: None

Advanced Settings (Recommended to improve accuracy)

Resolution

Binarize Image (Enhance Contrast for Clean Scans) Embed Full Fonts (Larger file, better compatibility)

Character Whitelist Preset

Only these characters will be recognized. Leave empty for all characters.

Character Whitelist (Optional)

Only these characters will be recognized. Leave empty for all characters.

Initializing...