Posted On: Jan 20, 2022

Amazon Rekognition content moderation is a deep learning-based feature that can detect inappropriate, unwanted, or offensive images and videos, making it easier to find and remove such content at scale. Amazon Rekognition provides a detailed taxonomy across 35 sub-categories and 10 distinct top-level moderation categories. On 11/05/2021, we launched an update with improved model for image moderation that reduces false positive rates across all of the moderation categories, particularly ‘explicit nudity’, without reduction in detection rates for truly unsafe content. Lower false positive rates imply lower volumes of flagged images to be reviewed further, leading to a better experience for human moderators and more cost savings.

Starting today, these content moderation accuracy improvements are available for Amazon Rekognition Video in all supported AWS Regions. To get started, you can try the latest version in the Amazon Rekognition Console. For more information on Amazon Rekognition content moderation, refer to feature documentation.