A game studio is building a mobile app that lets players scan a physical trading card with their phone camera and see the exact card's name and rarity displayed on screen, even though the studio has thousands of unique card designs. Which Azure AI service is best suited to this task, and which characteristic of the training data matters most? (Select TWO.)
Select all correct answers, then click Submit.
Short Explanation
Picture a player holding up a shiny trading card under their bedroom lamp versus outside in bright sun, and the app still needs to know exactly which card it is looking at out of thousands of possibilities. That calls for a vision service built to learn visual categories from example photos you supply and label yourself, since off-the-shelf image tagging would only say 'a card' rather than naming the specific one. But choosing the right service is only half the job. If the team only feeds it one pristine photo per card, the model has no idea what that card looks like when it is glared on, tilted, or dim, so it needs a spread of real-world example shots for each card to actually hold up when players scan with their phones. Reading text off descriptions has nothing to do with recognizing an image, so that path leads nowhere.
Full Explanation
The correct answers are A and C. Custom Vision is designed to let a team upload labeled photos of specific visual categories, in this case individual trading cards, and train a model that recognizes each one from a live camera feed, which matches the studio's need to distinguish thousands of distinct card designs. Alongside choosing that service, the model needs multiple representative images per card captured under varied lighting and angles, because a single clean reference shot will not generalize to the range of real-world phone camera conditions players will actually use, such as glare, tilt, or dim rooms. Option D is incorrect because key phrase extraction works on text, not on identifying a physical object from a camera image, so it has no role in recognizing a scanned card. Option B is incorrect because relying on a single reference image per card ignores the real variability of lighting and angle that a phone camera introduces, which would make the trained model unreliable in practice.