DRAG DROP
-
Match the types of computer vision workloads to the appropriate scenarios.
To answer, drag the appropriate workload type from the column on the left to its scenario on the right. Each workload type may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.
Image classification -> Generate captions for images. Object detection -> Locate vehicles in images. Optical character recognition (OCR) -> Extract movie title names from movie poster images.
OCR, OCR, Object Detection respectively, are the correct answers
Answer for 1 is: Object detection Image classification typically involves assigning a label or category to an entire image, while optical character recognition (OCR) is focused on identifying and recognizing text within images. On the other hand, object detection involves identifying and locating objects within an image, and this task is often extended to generate captions that describe the detected objects and their spatial relationships in the scene.
Sorry Object Detection, OCR, Object detection are correct
i will vote for object detection, OCR, object detection
ocr OCR Object detection
The Real Answer should be: Image Analysis, OCR, Object Detection. The question choices are incorrect, as Image Classification is not the same as Image Analysis service.
OCR, OCR, Objection Detection For the first one, "Which of the following generates captions for images", none of the answers provided work unless there is text of some sort in the image. Image classification would categorize the entire image into a class / label. The only vaguely viable answer for the first one is OCR.