A packaging company installs a camera above its bottling line. The system must read the expiration date text printed on each bottle cap and also draw a bounding box around any bottle that is missing its cap entirely so it can be automatically diverted off the line. Which two Azure AI Vision capabilities together satisfy these requirements? (Select TWO.)
Select all correct answers, then click Submit.
Short Explanation
You've got two jobs here: read the date on the cap and box the uncapped bottle. That's optical character recognition for the text and object detection for the location. Single-image labels or sentiment analysis won't tell the line which bottle to kick off.
Full Explanation
The correct capabilities are object detection and optical character recognition. Reading the expiration date printed on each cap requires extracting text from the image, which is optical character recognition, while identifying and locating any bottle missing its cap requires finding and marking the position of a specific object within the frame, which is object detection returning a bounding box. Together these two capabilities cover both stated requirements: reading text and locating a specific object. The image classification capability is incorrect because it only assigns one overall label to the entire image, such as bottle line normal or bottle line abnormal, and cannot pinpoint which specific bottle is missing a cap or where it is located on the line. The sentiment analysis capability is incorrect because it is a natural language processing capability that judges emotional tone in text, which has no application to a camera-based visual inspection task involving printed dates and physical bottle caps.