Aller au contenu
Atlas de l'IA

Reconnaissance optique de caractères

Lire le texte d’une image en caractères modifiables

Compréhension visuelleDébutant #15
entréeImageTexte

Le texte intégral est présenté en anglais ; le titre et le résumé sont localisés.

CE QUE DÉSIGNE CETTE CAPACITÉ

Takes an image containing text — a scan, a photo, a screenshot — and outputs the character sequence, usually with location boxes. It reads characters rather than interpreting them: the output is a transcription, not a meaning. Unlike document parsing, which also cares about layout such as tables, columns and reading order, OCR is only responsible for getting the characters right.

Comment c'est fait

The classic pipeline has two steps: a detection network finds quadrilateral boxes for lines or words, then each crop is passed to a sequence recogniser that decodes characters. Recognition moved from CNN plus recurrent layers with connectionist temporal classification to attention decoders and plain convolutional or Transformer designs. More recently, multimodal models transcribe end to end and handle irregular layouts better.

Produits représentatifs

5

Organisations concernées

Usages typiques

  • Field capture from invoices, receipts and IDs
  • Digitising paper archives and books
  • Street-sign and licence-plate reading
  • Copying text from screenshots and photos

Comment on l'évalue

Character error rate
Substitutions, deletions and insertions over the truth length
Word error rate
Word-level error rate, sensitive to segmentation
Detection F1
Localisation accuracy of text regions

Limites et points difficiles

  • Handwriting and poor scans — blurry, skewed, smudged — drive the error rate up sharply
  • Vertical text, mixed scripts and decorative fonts are frequently missed or misread
  • Tables and formulas come out as a character stream, losing row-column structure and super/subscripts

Concepts sous-jacents