본문으로 건너뛰기
AI 도감

문자 인식(OCR)

이미지 속 글자를 편집 가능한 텍스트로 읽는다

시각 이해입문 #15
입력이미지텍스트

이 페이지의 본문은 영어로 제공됩니다. 제목과 요약은 한국어로 번역되었습니다.

이 능력이 뜻하는 것

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.

기술적으로 구현하는 방법

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.

대표 제품

5

관련 기관

대표적 용도

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

성능을 평가하는 방법

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

경계와 난점

  • 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

뒤에 있는 개념