stmtify
← All guides
OCRJune 2, 20267 min read

How to Convert a Scanned Bank Statement to Excel (and What Accuracy to Expect)

Scanned statements are images, so they need OCR. How OCR conversion works, the accuracy to expect, and how to get the cleanest Excel result.

If your bank statement is a scan or a photo of a printed page, it isn't really “text” — it's a picture. A normal converter sees a blank page because there are no characters to read. To get those numbers into Excel you need OCR. Here's how it works and what to expect.

Digital vs scanned: a 5-second test

Open the PDF and try to highlight a number with your cursor. If it selects like text, you've got a digital statement and any method in our PDF-to-Excel guide will work. If nothing selects — or the entire page selects as a single block — it's scanned, and you need OCR.

What OCR actually does

OCR (optical character recognition) looks at the shapes in the image and works out which letters and digits they represent, turning the picture back into machine-readable text. A good statement converter then takes that recovered text and figures out the table structure — which numbers are dates, amounts, and balances. stmtify runs OCR directly in your browser, so even scanned statements are processed without uploading the file.

What accuracy can you realistically expect?

On a clean, straight, high-resolution scan, OCR is impressively good. But accuracy is only as good as the image, and it drops with:

  • low-resolution scans or small phone photos,
  • pages that are skewed, rotated, or curled,
  • faint ink, photocopies of photocopies, or coloured backgrounds,
  • shadows and glare from phone-camera shots.

The honest rule: treat OCR output as a very strong draft, not a final answer. A 0 misread as an 8, or a decimal point lost in a smudge, is the kind of error you won't notice unless you check.

How to get the cleanest scan

  • Scan at 300 DPI or higher rather than photographing the page.
  • Keep the page flat and square to the scanner — avoid skew.
  • Use black-and-white or greyscale, with good contrast.
  • If you must use a phone, get even lighting and fill the frame with the page.

Always verify scanned results

Because OCR can misread a character here and there, verification matters more than with digital statements:

  • Reconcile the opening and closing balances with the original.
  • Scan down the amount column for anything that looks off by a factor of ten.
  • Use stmtify's source-highlights view to confirm every transaction was captured, and the editable table to correct any misread digit before exporting.

Convert your bank statement with stmtify — it runs entirely in your browser, so your statement is never uploaded to a server. It's free, needs no signup, and works with statements from any bank.

Frequently asked questions

Can you convert a scanned bank statement to Excel?+

Yes, but it requires OCR (optical character recognition) to read the text out of the image first. A converter with built-in OCR can turn a scanned statement into an editable Excel or CSV file, though scanned results need closer checking than digital ones.

How accurate is OCR on bank statements?+

On clean, high-resolution scans, modern OCR is very accurate. Accuracy drops with low-resolution scans, skewed pages, faint ink, or busy backgrounds. Always verify totals and spot-check rows — treat OCR output as a strong draft, not a final answer.

How do I know if my statement is scanned or digital?+

Try to select a number with your cursor. If it highlights as text, it's a digital PDF and converts cleanly. If nothing selects, or the whole page selects as one image, it's scanned and needs OCR.

Convert your statement — privately

stmtify turns bank statement PDFs into Excel and CSV entirely in your browser. Nothing is uploaded, no signup, free.

Convert a bank statement

Related reading