Which AWS service is BEST suited for automatically detecting and analyzing objects, scenes, faces, and inappropriate content in large numbers of uploaded images and videos?

1 / 1
Select an answer
CorrectB

Explanation

Question Overview

Selecting an AI service specialized in image and video analysis.

Requirements to satisfy
  • 1「images and videos」Visual media are the analysis target = Rekognition
  • 2「objects, scenes, faces」Image recognition tasks
  • 3「automatically detecting and analyzing」Using machine learning through APIs
Per-option explanation
AIncorrect

Amazon Comprehend

Amazon Comprehend is a service that uses natural language processing (NLP) to extract sentiment and key phrases from text.

It is not a service that analyzes images or videos, so it is incorrect.

BCorrect

Amazon Rekognition

Correct. Amazon Rekognition is a managed AI service specialized in image and video analysis. It can perform object and scene detection, face analysis, and text extraction using only API calls, with no machine learning expertise.

CIncorrect

Amazon Polly

Amazon Polly is a service that converts text into natural speech (text-to-speech).

It is not a service that analyzes images or videos, so it is incorrect.

DIncorrect

Amazon Textract

Amazon Textract is a document-focused service that extracts text, tables, and forms as structured data from images such as scanned documents.

Even with the same image input, the requirement to detect objects, scenes, faces, and inappropriate content is handled by Rekognition, so it is incorrect.

Key Takeaway

'Image and video analysis', 'face recognition', and 'object detection' point to Amazon Rekognition. Text analysis is Comprehend, speech synthesis is Polly, and extracting text and tables from document images is Textract (document-focused). Distinguish AI services by input media and what they extract.

Related Links