Image & Video Tagging
Image and video tagging is a Filestack intelligence feature that returns keywords describing what appears in an image or video, with a confidence score for each keyword.
Image Tagging
Runs synchronously in the Processing API with the tags task, or as a task in Filestack Workflows. The Processing API request needs a security policy and signature.
Video Tagging
Runs only as a task in Filestack Workflows. By default it supports videos up to 10 minutes long. The Filestack sales team can raise this limit.
Result Format
Each tag has a score from 0 to 100. Example from the documentation: "sky": 76, "water": 93, "underwater": 85. Workflow logic can use the scores, for example tags.auto.sky gt 70.
Use Cases
- E-commerce: assigning product attributes
- Media companies: cataloging video archives
- Making media libraries searchable by keyword
Related terms
Intelligence (AI) Service
Machine learning tasks that tag, caption, moderate, scan and read files.
Workflows
Background processing of uploaded files with tasks and logic rules.
ContentIQ
Custom machine learning models that extract named fields from your documents.
Optical Character Recognition (OCR)
Intelligence service extracting printed and handwritten text from images.
More in Intelligence
This page is one of 94 terms in the Filestack glossary.
Browse all terms