Skip to main content

First recognize the text, then infer the rows and columns based on position and spacing, and export the TSV draft.

Select a text image, up to 12 MiB, 4 Megapixels.

The first time you use it, the recognition program and language data will be loaded from this website, and the pictures will not be uploaded. The maximum image size is 4 million pixels, and the results require manual proofreading.

Infer rows and columns based on text position and spacing, and only generate a TSV draft to be proofread; merged cells are not recognized, and complex tables may be misaligned.

Preview and results

After processing is complete, the results will be displayed here.

Instructions for use

  1. Select the table image and choose the language of the text in the image.
  2. Click "Extract table draft" to view the rows and columns inferred by text position.
  3. Manually proofread misaligned columns and missing words before using TSV; merging cells and complex tables is not guaranteed to be correct.

Input and output examples

Example input
table.png
Example output
table-draft.tsv

These are demo inputs and sample results, and do not mean that your data has been processed.

Calculation basis and reference materials

It is not a high-precision table structure model; it does not recognize merged cells, and complex tables are easily misaligned. Results must be manually proofread, and formula-style text will have a security prefix added.

Content check: · About this site and content description

Related tools