Image OCR Parse
/install image-ocr-parse
Image OCR Parse
What It Does
Extracts text from images via the PDFAPIHub hosted OCR API. Your image is uploaded to PDFAPIHub servers where Tesseract OCR processes it and returns the extracted text. Supports optional image preprocessing to improve OCR quality on low-resolution or noisy inputs.
When to Use
- Extract text from photos of receipts, signs, or documents
- OCR business cards, ID cards, or labels
- Process low-quality images with preprocessing
Required Inputs
Provide one of:
image_url— URL to an imagebase64_image— base64-encoded image- Multipart upload with
filefield
Authentication
This skill calls the PDFAPIHub hosted API at https://pdfapihub.com/api. Your image is uploaded to PDFAPIHub servers for OCR processing.
Send your API key in the CLIENT-API-KEY header.
Get your free API key at https://pdfapihub.com. Full API documentation is available at https://pdfapihub.com/docs.
Privacy note: Images you process are uploaded to PDFAPIHub's cloud service and the extracted text is returned. Do not send sensitive images unless you trust the service. Files are auto-deleted after 30 days.
Use Cases
- Receipt Scanning — Extract text from receipt photos for expense tracking
- Business Card Reader — OCR business card images to extract name, phone, email
- License Plate Recognition — Extract plate numbers from photos (with char_whitelist)
- Meter Reading — Extract digits from utility meter photos for automated logging
- Whiteboard Capture — OCR whiteboard or handwritten note photos into text
- Product Label Scanning — Extract ingredient lists or nutrition info from product label photos
Image Preprocessing Options
| Param | Default | Description |
|---|---|---|
grayscale |
false | Convert to grayscale |
sharpen |
false | Apply sharpening |
threshold |
0 | Binarization threshold (1–255) |
resize |
0 | Scale factor (max 4x) |
Example Usage
curl -X POST https://pdfapihub.com/api/v1/image/ocr/parse \
-H "CLIENT-API-KEY: your_api_key" \
-H "Content-Type: application/json" \
-d '{
"image_url": "https://pdfapihub.com/sample-invoicepage.png",
"lang": "eng",
"grayscale": true,
"sharpen": true,
"detail": "words"
}'
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install image-ocr-parse - 安装完成后，直接呼叫该 Skill 的名称或使用
/image-ocr-parse触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
Image OCR Parse 是什么？
Extract text from images via the PDFAPIHub cloud OCR API. Images are uploaded to pdfapihub.com for Tesseract OCR processing. Supports preprocessing (grayscal... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 81 次。
如何安装 Image OCR Parse？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install image-ocr-parse」即可一键安装，无需额外配置。
Image OCR Parse 是免费的吗？
是的，Image OCR Parse 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Image OCR Parse 支持哪些平台？
Image OCR Parse 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Image OCR Parse？
由 Rishabh Dugar（@rishabhdugar）开发并维护，当前版本 v1.0.2。