Microsoft Azure AI Fundamentals (AI-900)Describe features of computer vision workloads on AzureMedium
A museum wants to create an interactive exhibit where visitors can scan artwork with their phone camera, and the app will provide information about the artist and the painting. The system needs to accurately identify specific artworks from a predefined collection of thousands of paintings. Which computer vision capability is best suited for this task?
- AContent Moderator
- BCustom Vision (Classification)
- CImage Classification
- DImage Tagging
Show answer & explanationAnswer & explanation
Correct answer: B. Custom Vision (Classification)
Custom Vision (Classification) is ideal here because it allows training a model to classify images into highly specific categories (individual artworks) from a custom dataset. A pre-trained Image Classification model would likely not have knowledge of thousands of specific artworks.
Why the other options are wrong
- A. Content Moderator checks for inappropriate content, which is irrelevant to identifying artworks.
- C. Image Classification using a generic pre-trained model might categorize an image as 'painting' but won't identify a *specific* painting from a large custom collection.
- D. Image Tagging assigns general keywords, not specific artwork identification.
Custom Vision (Classification)
An Azure AI service feature used to train a custom image classification model that can categorize images into specific, user-defined classes based on provided training data.
- You provide the images and define the labels (classes).
- Ideal for niche classification tasks not covered by generic pre-trained models.
- Can be used to classify entire images or identify regions within images (object detection).
Memory trick: Custom Vision recognizes unique images with custom training.