Skip to content
Back to BlogTechnology

The Complete Guide to OCR Accuracy: What the Numbers Really Mean

Inkscribe AI Team July 15, 2025 8 min read

An OCR vendor says their product achieves 99.9% accuracy. Sounds impressive. But what does that actually mean for your 50-page contract? And why does the same engine produce 98% on one document and 84% on another?

This guide explains how OCR accuracy is measured, what affects it, and what you should actually demand when evaluating document processing tools.

How OCR Accuracy Is Measured

Accuracy is typically measured at two levels: character accuracy rate (CAR) and word accuracy rate (WAR). CAR counts correct individual characters; WAR counts correct complete words. A single wrong letter drops a whole word from the WAR count.

A vendor claiming "99.9% accuracy" is almost certainly reporting CAR on a clean test dataset. On a 500-character page, 99.9% CAR means one wrong character — that sounds fine. But in practice, that character might turn "not liable" into "now liable" in a contract clause.

Key Insight

Always ask vendors: Is this character or word accuracy? What document types were in the test set? Were they scanned or digital PDFs?

What Confidence Scores Tell You

Most OCR engines return a confidence score (0–100) alongside each extracted word. A score of 85+ is generally reliable; below 70 means the engine was uncertain. Inkscribe AI surfaces low-confidence words in the editor so you can review them before exporting.

Confidence scores are more useful than a single aggregate accuracy number because they tell you where the problems are, not just how many there are.

The 6 Biggest Factors That Affect OCR Accuracy

  1. Scan resolution: 300 DPI is the minimum for reliable OCR. Below 200 DPI, accuracy drops sharply. Modern smartphones produce 200–400 DPI scans; dedicated scanners produce 300–600 DPI.
  2. Document age and condition: Yellowed paper, ink bleeding, fold lines, and water damage all reduce contrast between text and background. Pre-processing (contrast enhancement, de-speckling) helps significantly.
  3. Font and type size: Serif fonts in 10pt+ are easy. Decorative fonts, very small text (below 8pt), and very large display text can all confuse engines.
  4. Complex layouts: Multi-column documents, tables with merged cells, text overlaid on images — these require layout detection in addition to character recognition.
  5. Handwriting: Printed handwriting (clear block capitals) achieves 90–95% accuracy. Cursive handwriting is genuinely difficult; 80–88% is realistic with modern AI models.
  6. Language and script: Latin-script languages (English, French, Spanish) are the most reliable. Arabic, Chinese, Japanese, and other non-Latin scripts require specialised models.

Engine Differences: Tesseract vs PaddleOCR vs AI Post-Processing

EngineBest ForWeaknessSpeed
Tesseract 5Clean digital PDFs, simple layoutsPoor on scans, no layout detectionVery fast
PaddleOCRScanned docs, complex layouts, non-Latin scriptsSlower than TesseractModerate
Claude AI post-processingCorrecting OCR errors, handwriting, context-aware fixesCannot be used alone — needs OCR firstAdds 2–5s

Inkscribe AI's hybrid pipeline runs Tesseract and PaddleOCR in parallel and uses Claude AI to reconcile differences and apply context — if the characters look like 'l' but the surrounding text makes 'I' (capital i) more plausible, the post-processor corrects it.

How to Benchmark OCR Accuracy for Your Documents

  1. Select 20 representative documents from your actual workflow — not the easiest ones.
  2. Manually transcribe a sample of each (or use a known ground truth).
  3. Run each engine and compute WER (word error rate) = substitutions + insertions + deletions / total words.
  4. Compare WER across engines on your specific document types.
  5. The engine with the lowest WER on your documents is the right one, regardless of vendor benchmarks.

Try It Yourself

Extract, translate, and analyse your documents in seconds — free to start.

Start Free — No Credit Card