Azure AI Services for Image Categorization and Captioning

AI-102 By islever Editorial Last updated

Short answer

CD Include image descriptions in Azure AI Computer Vision to generate captions and image type detection to categorize images as photographs or drawings.

Question

You are building an app that will share user images. You need to configure the app to perform the following actions when a user uploads an image: • Categorize the image as either a photograph or a drawing. • Generate a caption for the image. The solution must minimize development effort. Which two services should you include in the solution? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.
  1. object detection in Azure AI Computer Vision
  2. content tags in Azure AI Computer Vision
  3. image descriptions in Azure AI Computer Vision Correct Answer
  4. image type detection in Azure AI Computer Vision Correct Answer
  5. image classification in Azure AI Custom Vision

Key Takeaways

The exam tests the distinction between generic image classification and specific image type detection (photograph vs. drawing) while requiring caption generation, which is handled by image descriptions.

This question tests the selection of Azure AI Computer Vision features to categorize images as photographs or drawings and generate captions with minimal development effort. The correct solution leverages built-in image type detection and image description capabilities.

Common mistake: Many candidates select Object Detection or Custom Vision, confusing general object identification with high-level image type categorization or misunderstanding that Custom Vision requires training rather than being a plug-and-play API for simple tasks.

Expert Analysis

Why the Answer Is Correct

To minimize development effort, we must use pre-built Azure AI Computer Vision APIs rather than custom models. First, to categorize an image as either a photograph or a drawing, we use Image Type Detection (Option D). This feature specifically identifies the type of image content (e.g., photograph, illustration, or raw data), fitting the requirement perfectly. Second, to generate a caption, we use Image Descriptions (Option C). This feature automatically generates human-readable captions based on the visual content of the image. Together, these two services provide the required functionality without custom training.

Why the Other Options Are Wrong

Object Detection (A) identifies specific objects within an image (like 'dog' or 'car') but does not classify the entire image as a photo/drawing nor generate natural language captions. Content Tags (B) provide keywords describing the image but do not generate full sentences/captions. Image Classification (E) typically refers to Custom Vision, which requires building and training a model, violating the 'minimize development effort' constraint compared to using standard Computer Vision APIs.

Community Comment Notes

The community consensus strongly supports options C and D. Users note that 'Image Type Detection' is the specific API for distinguishing photos from drawings, whereas generic categorization might be too broad. Comments emphasize that generating captions is directly handled by the 'Image Descriptions' endpoint in the Computer Vision service.

Official Reference

These links open the official vendor documentation in a new tab.

Exam Strategy

When asked to 'minimize development effort,' always prefer managed, pre-trained Azure AI services over custom models like Custom Vision unless the task is highly specialized. Map specific requirements: 'caption' maps to Image Descriptions, and 'photo vs drawing' maps to Image Type Detection.

Frequently Asked Questions

Why not use Object Detection for categorizing photos?

Object detection finds specific items inside an image, not the overall image type. Image Type Detection classifies the whole image as a photo, drawing, etc.

Does Image Description generate captions automatically?

Yes, the Image Descriptions feature in Azure AI Computer Vision uses AI to generate human-readable captions describing the visual content.

More AI-102 FAQ →

Community Votes

CD
100%

100% of anonymous learners picked answer CD. Votes are pick records left by other test-takers — they are not the verified answer.

Discussion 11 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 11

  1. audlindr 👍 15
    I think Categorize the image as either a photograph or a drawing should be Image type detection https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-detecting-image-types Image Categorization doesn't identify image as photograph or drawing: See this: https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-categorizing-images Captions are generated using image descriptions in V3.2. However in V4.0 it is image captions https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-describing-images
  2. haverner 👍 3
    CE, Categorize instantly becomes Classification
  3. Jimmy1017 👍 1
    A. Object detection in Azure AI Computer Vision C. Image descriptions in Azure AI Computer Vision Explanation: Object Detection (option A): This service in Azure AI Computer Vision can be used to detect objects within an image. By analyzing the content of the image, it can identify whether the image contains elements typically found in photographs (e.g., people, landscapes) or drawings (e.g., sketches, illustrations). This information can help categorize the image accordingly. Image Descriptions (option C): Azure AI Computer Vision can generate descriptions for images, providing textual summaries of the content. These descriptions can include details about the objects detected in the image, providing additional context that can aid in categorization and caption generation.
  4. [Removed] 👍 1
    C e E Sim! E para classificar como imagem e C para descrever a imagem.
  5. takaimomoGcup 👍 1
    image descriptions and image type detection.
Show 6 more comments
  1. Harry300 👍 1
    CD imageType for photograph/drawing
  2. 4371883 👍 1
    this is in Oct 2024 exam
  3. reiwanotora 👍 1
    It must be C and D.
  4. HaraTadahisa 👍 1
    CD is the answer.
  5. chandiochan 👍 1
    Must be C & D
  6. Harry300 👍 1
    Should be CD

Reader comments & corrections

No reader corrections yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

Submitted for moderation before publishing. Keep it helpful and respectful.

Minimizing Dev Effort for Stream Anomaly Alerts

S-grade

Indexing Large OneDrive Files with Azure Video Indexer

S-grade

Maximizing Azure OpenAI Chatbot Response Accuracy

S-grade

OpenAI CLI Data Preparation Tool Supported File Formats

S-grade

← Back to AI-102 Study Guide