Local OCR Workspace

Recognize scanned PDFs and images in the browser, correct the text, and export TXT, Markdown, JSON, or a searchable image PDF.

Local processingOriginals preservedDirect export

Tool workspace

Processing stays in this tab
Do not mix PDF and image sources. Files are processed on the current device.

No files selected.

01

Pages and layout

Control render resolution, page range, and page segmentation.

02

Image preprocessing

Preprocessing is used for recognition only; searchable PDF output keeps the original color page.

Ready

Review and export

Text exports use your corrections; searchable PDF output uses OCR word coordinates.

Build searchable image PDF

Each page is rasterized and receives a nearly invisible OCR text layer. Original links, forms, and digital signatures are not preserved.

The font is read only in this tab and embedded in the output PDF; it is not uploaded or stored.
LOCAL
Models and files remain separate

PDFs and images are not sent to the model host. First use downloads only the OCR runtime and language data. Tesseract.js stores language data in browser IndexedDB, while the service worker caches runtime assets on demand.

How to use

  1. Choose one PDF or multiple images, then select Traditional Chinese, English, or mixed recognition.
  2. Prepare the model on first use, then choose pages, DPI, layout mode, and preprocessing.
  3. Review confidence and correct each page before exporting TXT, Markdown, JSON, or a searchable image PDF.

Privacy

Input and files are processed in the current browser tab. Mingmist does not receive the content unless you independently share the result elsewhere.

Limitations

Up to 80 pages/images are processed sequentially with one worker to limit memory risk. Tesseract.js does not parse PDFs directly, so pages are first rendered with PDF.js. Searchable PDF output rasterizes pages and removes original text, links, forms, attachments, annotations, and digital signatures. Manual corrections apply to text exports only and do not recalculate word coordinates.

FAQ

Are files uploaded?

No. PDFs and images are processed only in the current browser tab. First use downloads only OCR runtime assets and language data.

Why is the first run slower?

The OCR core and language data must be downloaded. Tesseract.js stores language data in browser IndexedDB, and the service worker caches runtime assets on demand.

Why does searchable PDF output need a font?

PDF standard fonts cannot encode CJK text. When results contain non-Latin characters, provide a TTF or OTF font that supports them.

Is recognition guaranteed to be correct?

No. Scan quality, fonts, tables, vertical text, columns, and handwriting affect results. Important content must be reviewed manually.