Guide

Scanned PDFs: what OCR gets wrong, and how to catch it

Updated

Optical character recognition is good enough that people trust it, which is the problem: its errors in tabular data are ones a human reader will not notice.

Talk to a specialist

Question 1

Open the PDF and try to select a line of text. What happens?

This one test separates the three fundamentally different cases, and it takes five seconds. Everything downstream depends on the answer.

The confusions are predictable

0 and O. 1 and l and I. 5 and S. 8 and B. 6 and G. Decimal points and commas that vanish or move.

In prose these are visible: a reader trips over them. In a column of account numbers or amounts they are invisible, because there is no context to make a wrong digit look wrong.

Input quality beats everything

A clean 300 dpi scan of an original document is worth more than any amount of software applied to a phone photograph of a photocopy.

So the first question is not which tool but whether a better input exists. A rescan takes minutes; correcting a bad recognition pass by hand takes hours and never quite finishes.

Three checks that catch most of it

Totals. If the document has a sum, recompute it from the extracted rows. A column that reconciles has probably survived intact.

Field shape. Account numbers, postcodes, dates and reference codes have formats, and a validation pass that flags anything not matching the pattern finds the recognition errors quickly.

A spot check by eye, taken from the middle of the document. The first page is the one that was tested when the settings were chosen.

Treat it as a draft

The useful discipline is to regard recognition output as a draft requiring verification rather than a result. That single framing change is what separates a project that works from one that quietly poisons a dataset.

Where the data will feed something consequential, an accounting system, a report, a decision about a person, budget for the checking rather than hoping it is unnecessary.

Have a lot of these, or one that will not behave?

Tell us what the documents are and how many. Data extraction suppliers who handle that kind of file will contact you directly.

Next: where to reach you.

  • Free, no obligation
  • We never ask you to upload a document here
  • No marketing lists, ever

One selection test, and you know the route

What happens when you select the text, what the data looks like, and whether it is personal. Three answers.

Sources

This site's own datasets, every figure quoted from its source and dated:

  • The Converter File Handling carries 14 published figures read from 11 sources' own pages; the 11 published figures given without a breakdown run from 7 to 90 day, read 11 November 2026.
  • The PDF to CSV Converter Index carries 36 published figures read from 30 sources' own pages; the 30 published figures given without a breakdown run from 5 to 1,500 USD (43 sources publish a figure), read 11 November 2026.
  1. gov.uk, publishing accessible documents
  2. UK GDPR Article 28, processor (legislation.gov.uk)
  3. UK GDPR Article 5, principles relating to processing (legislation.gov.uk)
  4. UK GDPR Article 32, security of processing (legislation.gov.uk)
  5. ICO, UK GDPR guidance and resources
  6. gov.uk, accessibility requirements for public sector websites and apps
Talk to a specialist