OCR

Scanned PDF to Excel with OCR

AlphaPDF Pro: $99/year · $12/month

An account and payment are required for PDF-to-JPG, all other converters and Premium tools. No free Premium jobs.

Recognize Scanned PDF content and export XLSX with AlphaPDF Premium. Select languages and review the recognized result.

What to expect

Turn recognized tables into spreadsheet worksheets for sorting and checking values. Use the original scan when available; adding resolution later cannot recover missing characters.

Non-tabular prose is not a workbook table. Verify totals, decimal separators and merged cells; formulas are not restored. Proofread names and numbers; handwriting is best-effort.

Start Scanned PDF to Excel with OCR

Sign in to start

Premium processing keeps every input and result scoped to your own account.

New to AlphaPDF? Create an account

Output quality is under review. This tool is not currently recommended as a reason to purchase Pro. Check all output against the source.

What it does

This tool reads the text in a scanned PDF and gives it back as an Excel workbook. Tables found on the page are written into worksheets so you can sort, total and check the figures. Running text outside tables is not part of the workbook. Scanned PDFs usually come from an office scanner or a scanning app, with one page per image. The cleaner the scan, the better the result, so use the original file rather than a copy that was printed and scanned again.

When to use it

Pick this for scanned bank statements, delivery notes, stock sheets or old ledgers where the numbers need to go into a spreadsheet. Instead of keying in each row, you get the table in cells and spend your time checking it. It works best when the table has clear lines between rows and columns.

How to use Scanned PDF to Excel with OCR

Sign in with an account that has Premium access.
Upload .pdf files. Each file can be up to 50 MB, with up to 25 files per batch.
The output is set to XLSX. Select the recognition languages and scan cleanup options. Review the available settings and choose a 1, 7 or 30-day retention period.
Start the job, then download and check the result before its retention period ends.

Related conversion options

Before you start

Non-tabular prose is not a workbook table. Verify totals, decimal separators and merged cells; formulas are not restored. Proofread names and numbers; handwriting is best-effort.

Before relying on the workbook, add a SUM under each column and compare it with the total printed on the statement. A mismatch points straight at the misread cell. Recognition is never perfect. Names, amounts and dates deserve a careful check, and handwriting is read on a best-effort basis. Select every language on the page so the right characters are expected.

Processing limits

Up to 50 MB per input; 25 files and 500 MB per batch. PDF limit: 2000 pages. Up to 2 active jobs per account. Output limit: 1000 MB. Renderer limits can reject especially large pages or images.

Example output

An inspected example is not available for this tool yet. Review the supported formats and limitations before processing.

Common questions

What if the statement spans several pages?

Tables on different pages usually land on separate sheets. Paste them together in Excel and check that no row was split in two at the page break.

My PDF already has text. Do I need OCR?

If you can select words in the PDF, it has a text layer. Try the regular PDF conversion tools first.

Will totals be recalculated?

No formulas are recreated. You get the values as read, so add formulas yourself and compare totals with the page.

Which languages can it read?

Choose the languages from the list before you start. Recognition works best when every language on the page is selected.