DemoOCR DotsOCR
Document page
Drop Image Here
- or -
Click to Upload
VLM prompt
Please output the layout information from the document image, including each layout element's bbox, category, and text content. 1. Bbox format: [x1, y1, x2, y2]. 2. Layout categories include Caption, Footnote, Formula, List-item, Page-footer, Page-header, Picture, Section-header, Table, Text and Title. 3. Format formulas as LaTeX, tables as HTML or Markdown, and normal text as Markdown. 4. Keep the original visible text without translation. 5. Sort all layout elements in human reading order. 6. Return one JSON object.
OCR JSON
Extract