AI-102 Question 114
Select 3You are designing an Azure AI solution to analyze images uploaded by users to a web application. The solution must extract detailed information about the content of the images, including objects, text, and tags describing the scene. Which features should you include in the image processing request using Azure Computer Vision?
- A
Object detection
- B
OCR (Optical Character Recognition)
- C
Generate thumbnail
- D
Image tagging
- E
Face detection
Show answer and explanation
Correct answers: A, B, D
Explanation
To analyze the image content and extract detailed information, you need to include features that detect objects, extract text, and generate descriptive tags. Object detection identifies objects in the image, OCR extracts text, and image tagging generates descriptive keywords. Generating thumbnails and face detection are not necessary based on the requirements of this specific use case.
- A. Correct.
Object detection is used to identify objects in an image, such as cars, animals, or furniture. This is necessary to extract detailed information about the image content.
- B. Correct.
OCR (Optical Character Recognition) is used to detect and extract text from images. This feature is necessary if the images may contain readable text.
- C. Incorrect.
Generate thumbnail is a feature for resizing and cropping images to create thumbnails, but it does not provide analysis of the image content. It is not required for this scenario.
- D. Correct.
Image tagging is used to generate descriptive tags for the image, such as 'beach', 'mountain', or 'outdoor'. This is essential to describe the scene in the image.
- E. Incorrect.
Face detection is used to detect and analyze faces in an image, but it is not explicitly required for this scenario unless facial analysis is needed.