Table of Contents
Which Azure service should you use to create image descriptions?
Learn which Azure service to use for creating automatic image descriptions. This AI-900 guide explains why Azure AI Vision is the correct choice for generating image captions and how it compares to Azure OpenAI and Azure Machine Learning.
Question
You need to build an app that will create descriptions of images. Which service should you use?
A. Azure OpenAI Service
B. Conversation language understanding (CLU)
C. Azure AI Vision
D. Azure Machine Learning
Answer
C. Azure AI Vision
Explanation
The correct service to use is C. Azure AI Vision. This service includes a specific, pre-trained feature designed to analyze and generate descriptions for images.
Understanding the Image Analysis Feature in Azure AI Vision
The Azure AI Vision service (formerly part of Cognitive Services) provides a range of pre-built computer vision capabilities. One of its key features is Image Analysis, which can generate a human-readable sentence that describes the content of an image. This process is also known as image captioning. When you submit an image to the service, the model:
- Identifies objects, beings, and actions within the image.
- Analyzes the relationships between these elements.
- Generates a descriptive caption in natural language based on its analysis.
Because this functionality is offered as a ready-to-use, pre-trained model within the Azure AI Vision service, it is the most direct and efficient solution for the task described.
Why Other Options Are Incorrect
A. Azure OpenAI Service: While powerful generative models available through Azure OpenAI, like GPT-4 with Vision, can create excellent image descriptions, Azure AI Vision offers this as a dedicated, built-in feature. For the AI-900 exam, when a specific pre-built cognitive service directly addresses the task, it is typically the intended answer over a more general-purpose platform.
B. Conversation language understanding (CLU): This service is part of Azure AI Language and is used to understand text-based or spoken commands. It cannot process image inputs.
D. Azure Machine Learning: This is a comprehensive platform for building, training, and deploying custom machine learning models from scratch. While you could use Azure Machine Learning to build your own image description model, it is a complex and time-consuming process. The question implies using an existing service, not building a new one.
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.