本文へスキップ
TakoAPI
スキル一覧に戻る

ocr-python

roamerxv 作

Image & Video Generation
—まだ評価がありません
あなたの評価

概要

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

説明

このスキルでできること

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.

使いどころ

  • 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

ワークフロー例

入力

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

エージェント
  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

出力

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

インストール

clawhub install roamerxv/ocr-python

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク