ocr-python
roamerxv 제작
Image & Video Generation요약
Optical Character Recognition (OCR) tool, supports Chinese and English text extraction from PDFs and images.
설명
이 스킬이 하는 일
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.
사용 시점
- 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
예시 워크플로
User asks: Extract all text from a scanned multi-page invoice PDF
- 1
Load the PDF using PyMuPDF and render each page as an image
- 2
Initialize PaddleOCR with Chinese-English language support
- 3
Run OCR prediction on each page image
- 4
Collect rec_texts and rec_scores from each page result
- 5
Return combined text with confidence scores per line
JSON list of recognized text strings with confidence scores for each detected line
설치
clawhub install roamerxv/ocr-pythonCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.