One still photo must produce a descriptive caption, content tags, detected objects, and any printed text, all from a single analysis request. Which option handles this?
Show answer and explanation
Answer: B
Image Analysis 4.0 can return captions, tags, objects, and read results for a still image in one call, selecting the visual features needed. Speech handles audio, Custom Vision would require a separately labeled dataset for each insight, and Video Indexer targets video files rather than one photo.
Why the other options are wrong
- A. Speech services work on audio, so they cannot analyze the visual content of a photo.
- C. Custom Vision builds models from your labeled images. It does not provide prebuilt captions or OCR for an arbitrary photo in one request.
- D. Video Indexer processes video and audio files for indexing. It is not the prebuilt choice for analyzing one still photo.