Saltar al contenido
Atlas de IA

Reconocimiento óptico de caracteres

Leer el texto de una imagen como caracteres editables

Comprensión visualPrincipiante #15
entradaImagenTexto

El texto completo se presenta en inglés; el título y el resumen están traducidos.

QUÉ SIGNIFICA ESTA CAPACIDAD

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.

Cómo se consigue técnicamente

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.

Productos representativos

5

Organizaciones relacionadas

Usos típicos

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

Cómo se evalúa

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

Límites y dificultades

  • 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

Conceptos detrás