Describe features of computer vision workloads on Azure →mediumMultiple ChoiceObjective-mapped

AI-900 Practice Question: Describe features of computer vision workloads on Azure

A retail company wants to use security cameras to automatically detect when products are removed from shelves. They need to identify the specific product type (e.g., a cereal box, a soda can) and count how many units are taken. Which Azure Computer Vision capability should they use?

⚠ Common exam trap

Many exam-takers confuse image tagging (which labels the whole scene) with object detection (which identifies and locates individual objects), leading them to choose option C when the question explicitly requires counting and identifying specific product types.

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

✓

Object detection

Object detection is the correct capability because it can both locate objects within an image (via bounding boxes) and classify them into specific categories (e.g., cereal box, soda can). This allows the system to identify the product type and count the number of units removed from shelves, which aligns directly with the requirement.

Answer analysis

Option-by-option breakdown

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

✗
Optical Character Recognition (OCR)
Why it's wrong here
Optical Character Recognition extracts text (printed or handwritten) from images. It is designed to digitize characters, not to understand the semantic content of a scene such as product types or their spatial layout. In a retail security camera context, OCR might read labels or shelf tags, but it cannot identify an arbitrary product or count multiple instances of a product because it lacks object-level detection. Thus, while useful for reading price tags, it cannot automate visual product inventory.
✓
Object detection
Why this is correct
Object detection is a computer vision task that produces both the category label and a bounding box for every instance of an object in an image. When applied to security camera frames, a model can be trained to recognize specific retail products, and by counting the predicted bounding boxes, the system can automatically tally how many units of each product are visible on shelves or in transit. This spatial localization distinguishes it from image-level classification and enables the inventory-counting automation the retail company needs.
✗
Image tagging
Why it's wrong here
Image tagging, also known as automated image annotation, assigns a set of descriptive labels or keywords to the entire image based on its overall content, typically using a multi-label classification model. It can output 'shelf,' 'soda can,' or 'bottle' as tags, but it does not provide per-instance localization or count; a tag is generated for the image as a whole regardless of how many objects are present. Therefore, while tagging can indicate which broad concepts are present, it cannot determine the quantity of each product type required for automated inventory management.
✗
Face detection
Why it's wrong here
Face detection is a specialized object detection variant that specifically locates human faces by finding facial landmarks and bounding boxes, often used for tasks like security, surveillance, or camera autofocus. In a retail setting, security cameras may use face detection to identify customers or count foot traffic, but it is not designed or trained to recognize non-human retail products such as packaged goods. Even if a face detection model were applied to a product image, it would fail to return any meaningful product labels or counts, making it wholly unsuitable for inventory automation.

Go deeper

AI-900 Practice Question: Describe features of computer vision workloads on Azure

Why each option matters

Option-by-option breakdown

Related to this question