A retail app needs a ready-made service that describes a single photo of a shelf with a sentence and detects the items in it, with no model training. Which option fits?
Show answer and explanation
Answer: C
Azure Vision Image Analysis is a prebuilt service that generates captions and detects objects in still images without custom training. The Read API only extracts text, Video Indexer targets video content, and a Custom Vision model requires you to train on labeled examples first.
Why the other options are wrong
- A. Video Indexer analyzes video streams and recordings for insights such as transcripts and scenes. It is not built for single still photos.
- B. The Read API extracts text from images and documents. It does not produce captions or detect objects in a shelf photo.
- D. Custom Vision needs labeled training images and a trained model before it can classify anything. That conflicts with the requirement for no custom training.