A convenience store wants a camera system to scan a photo of a stocked shelf and return the location and category of every individual product visible, such as three soda bottles in the upper left and two chip bags in the lower right, rather than a single label describing the whole photo. Which computer vision capability fits this need?
Select an answer to reveal the explanation.
Short Explanation
The giveaway here is that the store wants two things at once: what each item is, and where it sits on the shelf. A single label for the whole photo won't cut it, since that only tells you the picture shows a shelf, not that there are three sodas here and two chip bags there. Reading pixel by pixel gets you closer to shape, but it tends to blur together items of the same type sitting next to each other rather than counting them as separate things with their own boxes. And nothing here involves reading printed text off a label. What the store actually needs is a system that draws a little box around every individual product and tags each box with what's inside it, which is exactly the job built for locating and counting distinct objects in one image.
Full Explanation
The correct answer is C. The store needs both the location and the category of each distinct product on the shelf, which requires drawing a separate bounding box and label around every item, the defining behavior of object detection. Option A is incorrect because image classification produces one label for the entire photo, such as 'grocery shelf,' and cannot report where individual soda bottles or chip bags sit within the frame. Option B is incorrect because optical character recognition extracts printed text from an image, such as a price or brand name on a label, but it does not locate or categorize the products themselves. Option D is incorrect because semantic segmentation labels every pixel by category, which would show the outline of 'soda' pixels versus 'chips' pixels but does not separate touching instances into distinct, countable items with individual boxes the way object detection does. Object detection is the workload purpose-built for finding multiple discrete objects and their positions within a single image.