AI-900 Practice Question: Describe features of computer vision workloads on Azure

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✗

  Face detection identifies who the person is; face identification counts how many faces are present

  Why it's wrong here

  This statement reverses the roles of the two operations. Face detection merely outputs bounding boxes and possibly facial landmarks for any faces in an image; it does not identify who those people are. Face identification, in contrast, matches a detected face against an enrolled database to return a specific person's identity, rather than counting faces. Counting faces is just the number of detections, not an identification task.

• ✓

  Face detection finds face locations; face identification determines who the person is from an enrolled database

  Why this is correct

  This is correct: face detection first locates faces in an image or video frame, typically returning bounding-box coordinates around each face. Face identification then takes a detected face and compares its extracted feature vector (face embedding) to enrolled faces in a gallery or person group, returning the closest match or 'no match'. Azure Face API exposes separate operations for detection and identification, reinforcing that they are distinct pipeline stages.

• ✗

  Face detection works on videos; face identification works on static images only

  Why it's wrong here

  This option incorrectly describes the distinction as a matter of input modality. Both detection and identification operate on individual frames extracted from video as well as on still images; video support is not a defining characteristic. The real difference is what each operation does: detection localizes faces, whereas identification assigns an identity by matching against known subjects. Azure Face API works on any image or frame for either operation.

• ✗

  They are the same operation with different names

  Why it's wrong here

  Calling them the same operation ignores the fact that identification requires an enrolled set of known faces and a decision about similarity, while detection simply reports where faces are. Detection is a prerequisite for identification: you cannot identify a face that has not been located first. The underlying algorithms also differ, with identification involving feature extraction and distance comparison against gallery embeddings, not just face localization.

Go deeper

Related to this question