Back to workflow skills
AI and AgentsTesseract OCR image text extractionPW
AuthorCommunity author
AI and Agents Skill

Tesseract OCR image text extraction

Use Tesseract.js (OCR) to extract text from images. Supports multilingual recognition in Chinese and English, regional recognition, and character whitelist filtering.

0Uses8Likes10Views

What this skill does

Use Tesseract.js (OCR) to extract text from images. Supports multilingual recognition in Chinese and English, regional recognition, and character whitelist filtering.

  • Clarifies goals, inputs, and success criteria
  • Preserves evidence and marks uncertain boundaries
  • Produces structured, editable results
Installationnpx clawhub@latest install openlark/tesseract-image-ocrView source