Vision Options

Detect Labels

Detects instances of real-world labels within an image (JPEG or PNG) provided as input. This includes objects like flower, tree, and table; events like wedding, graduation, and birthday party; and concepts like landscape, evening, and nature.

Detect Labels Taxonomy

The taxonomy to apply the detected labels to.

Detect Labels Confidence

The minimum confidence (0-100) required to apply the returned label as tags. Default is 70.

Detect Moderation Labels

Detects explicit or suggestive adult content in a specified JPEG or PNG format image. Use this to moderate images depending on your requirements. For example, you might want to filter images that contain nudity, but not images containing suggestive content.

Detect Moderation Labels Taxonomy

The taxonomy to apply the detected moderation labels to.

Detect Moderation Labels Confidence

The minimum confidence (0-100) required to apply the returned label as tags. Default is 70.

Detect Celebrity Faces (Rekognition only)

Detects celebrity faces in the image. This will also detect non-celebrity faces. If you use this option, you should not use the Detect Faces option as either will overwrite the other. Detected faces will be stored as additional metadata for the image. If you are using Imgix, you can use this for cropping images centered on a face.

Detect Celebrity Faces Taxonomy (Rekognition only)

The taxonomy to apply the detected moderation labels to.

Detect Faces

Detects faces in the image. If you use this option, you should not use the Detect Celebrity Faces option as either will overwrite the other. Detected faces will be stored as additional metadata for the image. If you are using Imgix, you can use this for cropping images centered on a face.

Always Process in Background

Controls if Vision tasks are processed during an upload or queued to a background task to be processed at a later time (usually within a few minutes).

Ignored Tags

A comma separated list of tags to ignore.