AI-102 Question 160
Select 3You are developing a solution for a media company that wants to use Azure AI Video Indexer to analyze recorded video content for insights. The company requires the solution to extract spoken keywords, detect emotions in faces, and identify specific people appearing in the video. Which features of Azure AI Video Indexer should you configure to meet these requirements?
- A
Audio transcription and keyword extraction
- B
Face detection and emotion recognition
- C
Named entity recognition
- D
Face identification
- E
Optical character recognition (OCR)
Show answer and explanation
Correct answers: A, B, D
Explanation
Azure AI Video Indexer provides a wide range of capabilities, including transcription, keyword extraction, face detection, emotion recognition, and face identification. For this scenario, the required insights include spoken keywords, emotions in faces, and identification of specific people. Therefore, the appropriate features to configure are audio transcription and keyword extraction for spoken content, face detection and emotion recognition for analyzing emotions, and face identification for recognizing specific individuals.
- A. Correct.
Audio transcription and keyword extraction is required to analyze spoken content and extract keywords from the video.
- B. Correct.
Face detection and emotion recognition are needed to detect individuals' faces and analyze their emotions.
- C. Incorrect.
Named entity recognition is used to identify named entities in text but is not directly applicable to detecting faces or spoken keywords in this scenario.
- D. Correct.
Face identification is required to recognize specific people appearing in the video based on pre-trained facial models.
- E. Incorrect.
Optical character recognition (OCR) is used to extract text from visual content, which is not required for this scenario.