Image Classification and Object Detection Features - AI-102 Exam Solution

Correct Answer:B and C.

Option A is INCORRECT.

Definition 1 “Performs application of one or more labels to image and also returns image coordinates where the applied label(s) can be found.” corresponds to “Object Detection.”

Option B is CORRECT.

“Performs application of one or more labels to image” corresponds to “Image classification.”

Option C is CORRECT.

“Performs application of one or more labels to image, and also returns image coordinates where the applied label(s) can be found.” corresponds to “Object Definition.”

Option D is INCORRECT.

Definition 1 “Performs application of one or more labels to image, and also returns image coordinates where the applied label(s) can be found.” corresponds to “Image Classification.”

Reference:

Custom Vision functionality is a machine learning service provided by Microsoft Azure that allows developers to train, deploy, and manage custom image classifiers and object detectors without requiring expertise in machine learning. It offers two primary features: image classification and object detection.

Image Classification is a feature of Custom Vision that allows developers to apply one or more labels to an image. It works by training a machine learning model on a set of labeled images and then using the trained model to classify new images. The result of image classification is a set of labels assigned to an image. This feature is useful in scenarios where developers want to identify the contents of an image based on the assigned labels.

Object Detection is another feature of Custom Vision that allows developers to apply one or more labels to an image and also returns image coordinates where the applied label(s) can be found. Object Detection works by training a machine learning model on a set of labeled images that also have bounding boxes around the objects of interest. The result of object detection is a set of labels assigned to an image and the coordinates of bounding boxes around each object. This feature is useful in scenarios where developers want to identify and locate specific objects within an image.

Based on the above definitions, the correct matches between the features and definitions are:

• Feature 1 (Image Classification) --> Definition 2 (Performs application of one or more labels to image.)
• Feature 2 (Object Detection) --> Definition 1 (Performs application of one or more labels to image, and also returns image coordinates where the applied label(s) can be found.)

Therefore, the correct answer is:

B. Feature 1 --> Definition 2 C. Feature 2 --> Definition 1