Skip to Content

AI-900: Which Functionalities Do Azure AI Vision Models Support and What Are Their Limitations?

Learn about the key capabilities of Azure AI Vision models, including image captioning, object detection, and image classification. Discover why speech recognition is not a supported feature and how these tools can enhance your AI projects effectively.

Table of Contents

Question

Which of the following functionalities is NOT directly supported by the pre-built Azure AI Vision models?

A. Image captioning
B. Speech recognition
C. Object detection
D. Image classification

Answer

B. Speech recognition

Explanation

The pre-built Azure AI Vision models do not directly support Speech recognition. While Azure AI offers various AI services, including speech recognition in Azure Cognitive Services, pre-built Azure AI Vision models specifically focus on visual analysis and do not directly support speech recognition functionalities. To use the Azure AI Vision service, you need to create a dedicated “Azure AI Vision” or a broader “Azure AI Services” resource within your Azure subscription, depending on your needs. Once set up, you can submit images to Azure AI Vision for various analyses, including:

  • Optical Character Recognition (OCR): Extracting text embedded within images.
  • Image Captioning: Generating textual descriptions of the image content.
  • Object Detection: Identifying and locating objects within images, providing details including bounding boxes and confidence scores.
  • Image Tagging: Assigning relevant keywords to describe the image content, and facilitating categorization and search based on these tags.

The pre-built Azure AI Vision models directly support image classification. Azure AI Vision provides pre-built models for classifying images into different categories based on their content.

The pre-built Azure AI Vision models directly support object detection. Azure AI Vision models can identify and locate objects within images, returning their positions and details.

The pre-built Azure AI Vision models directly support image captioning. Pre-built models can analyze and generate descriptions of the content depicted in images.

Which Functionalities Do Azure AI Vision Models Support and What Are Their Limitations?

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.