Skip to main content

Addons - Image Analysis

Automatic image tagging, content analysis, and OCR text extraction.

FileSpin's Image Analysis addon runs vision analysis on uploaded images using Google Vision AI and extracts structured metadata that's stored alongside the asset and indexed for search:

  • Auto-tagging — labels with confidence scores describing the contents of the image (objects, scenes, concepts).
  • Best-guess labels — a short summary describing the image as a whole.
  • OCR (text extraction) — reads text inside images (screenshots, signs, product labels, documents) and indexes it for keyword search. Words shorter than 3 characters are excluded; up to 500 words are indexed per image.

All extracted data is searchable through the standard search API. The addon can be triggered on-demand via the API below, or run automatically as part of the Automated Media Pipeline.

For the conceptual overview and end-user feature description, see Image Analysis (AI). For automating this addon on upload or metadata change, see Automated Media Pipeline.