1. A retailer wants to use Azure Content Understanding to extract structured visual characteristics — such as dominant colors, detected brand logos, and product category — from a large batch of catalog images, and wants a single configured pipeline to consistently apply the same extraction schema across all images. Which processing approach is MOST appropriate?
- A. A single-task Content Understanding pipeline invoked separately and inconsistently per image with ad hoc prompts
- B. A pro-mode Content Understanding pipeline defined once with a consistent extraction schema and reused across the batch✓ Correct
- C. Manual visual inspection by a human reviewer for each image in the catalog
- D. A speech-to-text pipeline applied to product description audio narrations
Explanation
A pro-mode Content Understanding pipeline lets you define a reusable, structured extraction schema (colors, logos, category) once and apply it consistently across a batch, which is exactly the stated need for uniform structured extraction at scale. Option A describes ad hoc, per-image prompting without a consistent schema, which risks inconsistent output across the catalog. Option C does not scale and is not an Azure AI capability. Option D is the wrong modality — it processes audio, not visual catalog images.