Zum Inhalt springen
TakoAPI
Zurück zu den Skills

ocr-python

von roamerxv

Image & Video Generation
—Noch nicht bewertet
Deine Bewertung

Kurzbeschreibung

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

Beschreibung

Was dieser Skill macht

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.

Wann du ihn einsetzt

  • 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

Beispiel-Workflow

EINGABE

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

AGENT
  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

AUSGABE

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

Installation

clawhub install roamerxv/ocr-python

Führe den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.

Links