image-ocr

Extract text from images (JPG, PNG, WebP) using OCR powered by PDF API Hub

Package Information

Downloads: 3 weekly / 39 monthly
Latest Version: 1.0.1
Author: Rishabh Dugar

Documentation

n8n-nodes-image-ocr

NPM Version
License

Extract text from images (JPG, PNG, WebP) using OCR — with preprocessing options for best accuracy.

This is an n8n community node powered by PDF API Hub.


🚀 Install

  1. Go to Settings → Community Nodes in n8n
  2. Enter n8n-nodes-image-ocr
  3. Click Install

🔑 Setup

Sign up at pdfapihub.com → copy your API key → add to n8n credentials.


✨ Features

Parameter Description
Input Type URL, Base64, or Binary file
Language English, Portuguese, Russian — combinable with +
Detail Level Text or Words (with bounding boxes)
Output Format JSON or plain Text

Advanced Options

Option Description
Threshold Binarization threshold (0–255) for better contrast
Grayscale Convert to grayscale before OCR
Sharpen Sharpen image for clearer text
Resize Scale Scale image up (0–4×) for tiny text
Character Whitelist Restrict recognized characters
PSM / OEM Page segmentation and engine modes

💡 Use Cases

  • Business cards — extract contact info from photos
  • Whiteboard capture — digitize meeting notes from photos
  • Screenshots — extract text from app screenshots
  • Product labels — read text from product images

License

MIT

Discussion