Exam AWS Certified Solutions Architect - Associate SAA-C03 topic 1 question 57 discussion

Option A, using Amazon Comprehend, is not a good fit for this use case because Amazon Comprehend is a natural language processing service that is designed to analyze text, not images. Option C, using Amazon SageMaker to detect inappropriate content, would require significant development effort to build and train a custom machine learning model. It would also require a large dataset of labeled images to train the model, which may be time-consuming and expensive to obtain. Option D, using AWS Fargate to deploy a custom machine learning model, would also require significant development effort and a large dataset of labeled images. It may not be the most efficient or cost-effective solution for this use case. In summary, the best solution is to use Amazon Rekognition to detect inappropriate content in images, and use human review for low-confidence predictions to ensure that all inappropriate content is detected.

https://aws.amazon.com/rekognition/content-moderation/ Amazon Rekognition Content Moderation automates and streamlines your image and video moderation workflows using machine learning (ML), without requiring ML experience.