paddleocr-text-recognition
Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字, plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan,…
- installs 8w
- 87
- 30-day movement
- starts with the next reading
- Related entries
- 2
- Connections
- 0
An agent skill that wraps PaddleOCR to extract text from images, photos, scans, screenshots, and scanned PDFs. It returns machine-readable strings with line-level text and optional bounding-box coordinates, with documented preprocessing options and a CLI reference.
Reach for it when a task needs accurate OCR, especially for CJK text, small print, or handwriting, with optional position data.
Use it to
- Extract text from screenshots or photos
- OCR scanned PDFs into plain text
- Get text with bounding-box coordinates
- Recognize CJK or handwritten text
- Run OCR via the paddleocr CLI
For Developers needing OCR in agent workflows
- Host repository
- PaddlePaddle/PaddleOCR
- Installs, lifetime
- 564
- Installs, 8 weeks
- 87
- Licence
- Apache-2.0
- Host stars
- 90k
- Host language
- Python