Tag Image Activity
The Tag Image activity identifies and extracts content tags for recognizable objects, living beings, scenery, and actions within an image. It processes both foreground subjects and background settings to provide a comprehensive list of visual elements without hierarchical constraints.
| Field | Description | Requirement |
|---|---|---|
| Ocp Apim Subscription Key | The unique API key for the Microsoft Computer Vision service. | Required |
| Endpoint | The specific URL endpoint for the Microsoft Computer Vision API. | Required |
| Image Url | The public URL address of the image file to be processed. | Required |
| Response variable name | The name of the variable designated to store the HTTP response. | Required |
Action Types & Examples
Image Tagging
- Format: JSON string
- Example Result:
{"tags": [{"name": "outdoor", "confidence": 0.99}, {"name": "building", "confidence": 0.98}]}
Implementation Examples
Field Setup - Ocp Apim Subscription Key: 2dfc034684a3434fb3270534c5efdc66 - Endpoint: https://yourapiurl.cognitiveservices.azure.com/ - Image Url: http://example.com/images/test.jpg
Execution Parameters - Response variable name: getResponse
Technical Notes
This activity utilizes Microsoft Cognitive Services to analyze images. Tagging is comprehensive and includes settings, furniture, tools, plants, and accessories rather than just the primary subject. For further details, refer to the official Microsoft Computer Vision documentation regarding image tagging features.