Skip to content

Explicit Content Detection Activity

The Explicit Content Detection activity identifies explicit content, such as adult or violent material, within an image. It analyzes the image across five categories: adult, spoof, medical, violence, and racy, returning the likelihood of each category's presence.

Field Description Requirement
Api key Google Cloud Vision API Key Required
Image path/url URL of the image in Google Cloud Storage Optional
Base64 Base64 encoded string of the image file Optional
Response variable name Name of the variable to store the HTTP response Required

Action Types & Examples

Detect Content

  • Format: JSON String
  • Example Result: {"adult": "VERY_UNLIKELY", "spoof": "UNLIKELY", "medical": "POSSIBLE", "violence": "VERY_UNLIKELY", "racy": "LIKELY"}

Implementation Examples

Field Setup - Api key: bb3c53c6-8515-4e34-97c8-8281de60972d - Image path/url: gs://cloud-samples-data/vision/ocr/sampleimage.jpg - Base64: /9j/4AAQSkZJRgABAQEAYABgAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMDAsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/2wBDAQMEBAUEBQkFBQkUDQsNFBQUF……………./58x/8BX+R/9k= - Response variable name: getResponse

Execution Parameters - Scenario 1: Using Image URL - Api key: bb3c53c6-8515-4e34-97c8-8281de60972d - Image path/url: gs://cloud-samples-data/vision/ocr/sampleimage.jpg - Response variable name: detectionResult - Scenario 2: Using Base64 String - Api key: bb3c53c6-8515-4e34-97c8-8281de60972d - Base64: /9j/4AAQSkZJRgABAQEAYABgAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMDAsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/2wBDAQMEBAUEBQkFBQkUDQsNFBQUF……………./58x/8BX+R/9k= - Response variable name: detectionResult

Technical Notes

For detailed information regarding Google Cloud Vision's SafeSearch features, refer to the official documentation: Detect Explicit Content (SafeSearch).

The Image path/url and Base64 fields are mutually exclusive; only one of these fields should be configured for the activity to execute successfully.

The Response variable name will store the HTTP response as a JSON string, which can then be parsed to access the likelihood scores for each content category.