Image Analysis
- ClaireT (Deactivated)
- Ittihad Chowdhury
- Lane Schechter
Partners may request analysis data for individual images. GumGum Contextual’s image analysis produces keywords and brand safety scoring.
GumGum Contextual image analysis works by applying computer vision (CV) processing to the specified image.
Image Analysis Response
Image analysis data is aggregated into the following GumGum Contextual image classification report sections:
Keywords
Extracts and scores image keywords according to prominence.Brand Safety
Identifies and scores brand safety threats according to GumGum's Threat classification taxonomy, in compliance with GARM’s Brand Safety Floor.
The format is JavaScript Object Notation (JSON) Content-Type: application/json; charset=UTF-8.
Image Analysis Categories and Keywords
GumGum Contextual image analysis includes threat classifications identified by computer vision object detectors and scene classifiers, plus contextual targeting keywords.
Brand Safety (Threat) Categories | Keywords |
|---|---|
Violence | Contextual targeting keywords |
Supported Image Formats
GumGum Contextual Response Format
The GumGum Contextual API response format is JavaScript Object Notation (JSON) Content-Type: application/json; charset=UTF-8.
Related Articles
Related content
The contents of these documents and any attachments contain GumGum, Inc. confidential information and are legally protected from disclosure.