Перейти к содержимому
TakoAPI
Назад к навыкам

ocr-python

от roamerxv

Image & Video Generation
—Ещё нет оценок
Ваша оценка

Кратко

Optical Character Recognition (OCR) tool, supports Chinese and English text extraction from PDFs and images.

Описание

Что делает этот навык

OCR tool built on PaddleOCR that extracts text from images and PDFs. Supports Chinese and English, including mixed-language documents. Returns recognized text alongside per-line confidence scores.

PaddleOCR handles Chinese-English mixed content reliably, which most OCR libraries do not support without extra configuration.

Когда его использовать

  • Extract text from scanned invoice PDFs
  • Recognize printed text in product photos
  • Convert scanned contracts to editable text
  • Pull text from screenshots for data pipelines
  • Digitize multi-page printed forms

Пример сценария

ВВОД

User asks: Extract all text from a scanned multi-page invoice PDF

АГЕНТ
  1. 1

    Load the PDF using PyMuPDF and render each page as an image

  2. 2

    Initialize PaddleOCR with Chinese-English language support

  3. 3

    Run OCR prediction on each page image

  4. 4

    Collect rec_texts and rec_scores from each page result

  5. 5

    Return combined text with confidence scores per line

ВЫВОД

JSON list of recognized text strings with confidence scores for each detected line

Установка

clawhub install roamerxv/ocr-python

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки