A transportation company wants to automatically identify whether an image contains a car, a truck, or a motorcycle. The system should output a single label for the entire image. Which computer vision capability in Azure should they use?
Trap 1: Object detection
Object detection locates objects with bounding boxes and provides multiple labels per image, not a single overall label.
Trap 2: Optical Character Recognition (OCR)
OCR extracts printed or handwritten text from images and is not used for recognizing vehicle types.
Trap 3: Semantic segmentation
Semantic segmentation classifies each individual pixel in an image, which is more detailed than simply labeling the entire image.
- A
Object detection
Why wrong: Object detection locates objects with bounding boxes and provides multiple labels per image, not a single overall label.
- B
Image classification
Image classification assigns one or more labels to the entire image, matching the requirement to identify the type of vehicle shown.
- C
Optical Character Recognition (OCR)
Why wrong: OCR extracts printed or handwritten text from images and is not used for recognizing vehicle types.
- D
Semantic segmentation
Why wrong: Semantic segmentation classifies each individual pixel in an image, which is more detailed than simply labeling the entire image.