Process your media with computer vison via Amazon Rekognition or Google Vision. Automatically tag images, perform content moderation and detect faces for smart cropping.
Setting Up Vision
The Vision feature of Media Cloud enables automatic image tagging and classification using machine learning image classification services like Amazon Rekognition and Google Cloud Vision. In addition to image tagging, these services can be used to detect explicit images for moderation purposes, detect faces and detect celebrities (Amazon Rekognition only). …
Setting Up Amazon Rekognition
You must be using Amazon S3 as your cloud storage provider to use Rekognition for Vision processing. Rekognition will use all of the same connection info as cloud storage, so to get Rekognition working requires only a few added steps. If you haven’t already setup Amazon S3 cloud storage, you …
Setting Up Google Vision
Google Cloud Vision, unlike Rekognition, can be used with any cloud storage provider. If you’ve configured Google as your cloud storage provider, the only thing you need to do is enable the Cloud Vision API in Google Console. For other cloud storage providers, you’ll need to follow the first four steps …
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 …