Implement computer vision solutions →easyMultiple Choice

AI-102 Implement computer vision solutions Practice Question

Exhibit

Refer to the exhibit.

```json
{
  "url": "https://example.com/image.jpg",
  "maxCandidates": 1,
  "language": "en"
}
```

Response:
```json
{
  "captionResult": {
    "text": "a person holding a smartphone",
    "confidence": 0.89
  },
  "metadata": {
    "height": 600,
    "width": 800
  },
  "modelVersion": "2024-02-01"
}
```

Refer to the exhibit. An Azure Cognitive Services Computer Vision API call for image captioning is returning only one caption. The developer wants to get three possible captions ranked by confidence. Which parameter should be modified in the request?

⚠ Common exam trap

Watch out — candidates often confuse the `maxCandidates` parameter with other parameters like `language` or `details`, or assume that changing the API version or image source would increase the number of captions, when in fact the default behavior is to return only one caption unless explicitly overridden.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Set the maxCandidates value to 3.

The `maxCandidates` parameter in the Computer Vision Image Analysis API controls the maximum number of captions returned in the response. By default, this value is 1, so only the top-ranked caption is returned. Setting `maxCandidates=3` instructs the API to return up to three captions, each with its own confidence score, ranked from highest to lowest confidence.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Use a different API version, such as 2023-04-01.
Why it's wrong here
Changing the API version does not alter caption count; the number of captions is governed by the maxCandidates request parameter, which defaults to one. Version switching is tempting because newer releases add features. Setting maxCandidates=3 returns three captions ranked by confidence.
✗
Modify the URL to point to a different image.
Why it's wrong here
Changing the image URL alters which picture is analysed, not how many captions the service returns. The maxCandidates parameter controls caption count. Pointing at a different image is tempting when the current one yields poor results, but it cannot produce three ranked captions for the same image.
✗
Change the language parameter to 'multi'.
Why it's wrong here
The language parameter selects the caption's output language, not the number of candidates returned. Multiple ranked captions require the maxCandidates parameter. Setting language to 'multi' is tempting when localisation is needed, but it governs translation of a single caption rather than generating several alternatives.
✓
Set the maxCandidates value to 3.
Why this is correct
The maxCandidates parameter controls how many alternative captions the Image Captioning service returns, each with a confidence score. Setting it to 3 satisfies the requirement for three ranked captions; leaving it at the default of 1 explains why only one caption currently appears.

Go deeper

AI-102 Implement computer vision solutions Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question