Azure AI-102 exam questions with |\ |\ |\ |\ |\
answers
You want to use the Azure AI Vision Analze Image function to
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
generate an appropriate caption for an image. Which visual feature
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\
should you specify? |\ |\
A. Tags
|\
B. DenseCaptions
|\
C. Objects - CORRECT ANSWERS ✔✔B. Dense Captions
|\ |\ |\ |\ |\ |\ |\
What is the purpose of the Azure AI Vision service?
|\ |\ |\ |\ |\ |\ |\ |\ |\
A. To provide functionality for audio transcription
|\ |\ |\ |\ |\ |\
B. To extract information from images
|\ |\ |\ |\ |\
C. To detect the presence and location of specific sounds within an
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
audio file - CORRECT ANSWERS ✔✔B. To extract information
|\ |\ |\ |\ |\ |\ |\ |\ |\
from images |\
How many images per class do you need to Tran a custom image
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
classification model with Azure AI Vision? |\ |\ |\ |\ |\
A. At least 10
|\ |\ |\
B. About 3-5
|\ |\
C. About 8 - CORRECT ANSWERS ✔✔B. About 3-5
|\ |\ |\ |\ |\ |\ |\ |\
,How can you access your custom image classification model after
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\
training it with Azure AI Vision?
|\ |\ |\ |\ |\
A. Through APIs or Vision Studio
|\ |\ |\ |\ |\
B. Only through APIs
|\ |\ |\
C. Only in the browser - CORRECT ANSWERS ✔✔A. Through
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\
APIs or Vision Studio
|\ |\ |\
What are the two types of custom models that you can train with
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
Azure AI Vision? |\ |\
A. Image segmentation and image enhancement
|\ |\ |\ |\ |\
B. Image classification and object detection
|\ |\ |\ |\ |\
C. Image captioning and image generation - CORRECT ANSWERS
|\ |\ |\ |\ |\ |\ |\ |\ |\
✔✔B. Image classification and object detection
|\ |\ |\ |\ |\
Which of the following facial attributes can be Azure AI Vision
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
service predict? |\
A. Location
|\
B. Type of eye-glasses
|\ |\ |\
C. Occlusion - CORRECT ANSWERS ✔✔A. Location
|\ |\ |\ |\ |\ |\
,You need to create a facial recognition solutions to identify named
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
employees. Which service should you use? |\ |\ |\ |\ |\
A. Azure AI Vision
|\ |\ |\
B. Azure AI Custom Vision
|\ |\ |\ |\ |\
C. Face - CORRECT ANSWERS ✔✔C. Face
|\ |\ |\ |\ |\ |\
You need to verify that the person in a photo taken at hospital
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
reception is the same person in a photo taken at a ward entrance 10
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
minutes later. What should you do? |\ |\ |\ |\ |\
A. Create a People Group and add a person for every hospital visitor
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
with multiple photographs to train a model
|\ |\ |\ |\ |\ |\ |\
B. Verify the face in the ward photo by comparing it to the detected
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
Face ID from the reception photo
|\ |\ |\ |\ |\
C. Compare the Age, head pose, and hair color for the faces in the
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
reception and ward photo's. - CORRECT ANSWERS ✔✔B. Verify
|\ |\ |\ |\ |\ |\ |\ |\ |\
the face in the ward photo by comparing it to the detected Face ID
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
from the reception photo
|\ |\ |\
Which API would be best for this scenario? You need to read a large
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
number of files with high accuracy. The Text is short sections of
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
handwritten text, some in English and some of it is in multiple |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
languages.
A. A custom Language API
|\ |\ |\ |\
B. Document Intelligence API
|\ |\ |\
, C. Image Analysis API - CORRECT ANSWERS ✔✔C. Image
|\ |\ |\ |\ |\ |\ |\ |\ |\
Analysis API |\
What levels of divisions are the OCR results returned?
|\ |\ |\ |\ |\ |\ |\ |\
A. Only total content and pages of text
|\ |\ |\ |\ |\ |\ |\
B. Blocks, words and lines of text
|\ |\ |\ |\ |\ |\
C. Total content, image tags, pages, words and lines of text -
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
CORRECT ANSWERS ✔✔B. Blocks, words and lines of text |\ |\ |\ |\ |\ |\ |\ |\
You've scanned a letter into PDF format and need to extract the text
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
it contains. What should you do?
|\ |\ |\ |\ |\
A. Use the Azure AI Custom Vision service
|\ |\ |\ |\ |\ |\ |\
B. Use the Image Analysis API of the Azure AI Vision service
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
C. Use the Document Intelligence API - CORRECT ANSWERS
|\ |\ |\ |\ |\ |\ |\ |\ |\
✔✔C. Use the Document Intelligence API
|\ |\ |\ |\ |\
You want Azure Video Indexer to analyze a video. What must you
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
do first?
|\
A. Use the Azure AI Vision service to extract key frames from the
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
video
B. Upload the video to Azure Video Indexer and index it
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\
answers
You want to use the Azure AI Vision Analze Image function to
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
generate an appropriate caption for an image. Which visual feature
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\
should you specify? |\ |\
A. Tags
|\
B. DenseCaptions
|\
C. Objects - CORRECT ANSWERS ✔✔B. Dense Captions
|\ |\ |\ |\ |\ |\ |\
What is the purpose of the Azure AI Vision service?
|\ |\ |\ |\ |\ |\ |\ |\ |\
A. To provide functionality for audio transcription
|\ |\ |\ |\ |\ |\
B. To extract information from images
|\ |\ |\ |\ |\
C. To detect the presence and location of specific sounds within an
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
audio file - CORRECT ANSWERS ✔✔B. To extract information
|\ |\ |\ |\ |\ |\ |\ |\ |\
from images |\
How many images per class do you need to Tran a custom image
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
classification model with Azure AI Vision? |\ |\ |\ |\ |\
A. At least 10
|\ |\ |\
B. About 3-5
|\ |\
C. About 8 - CORRECT ANSWERS ✔✔B. About 3-5
|\ |\ |\ |\ |\ |\ |\ |\
,How can you access your custom image classification model after
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\
training it with Azure AI Vision?
|\ |\ |\ |\ |\
A. Through APIs or Vision Studio
|\ |\ |\ |\ |\
B. Only through APIs
|\ |\ |\
C. Only in the browser - CORRECT ANSWERS ✔✔A. Through
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\
APIs or Vision Studio
|\ |\ |\
What are the two types of custom models that you can train with
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
Azure AI Vision? |\ |\
A. Image segmentation and image enhancement
|\ |\ |\ |\ |\
B. Image classification and object detection
|\ |\ |\ |\ |\
C. Image captioning and image generation - CORRECT ANSWERS
|\ |\ |\ |\ |\ |\ |\ |\ |\
✔✔B. Image classification and object detection
|\ |\ |\ |\ |\
Which of the following facial attributes can be Azure AI Vision
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
service predict? |\
A. Location
|\
B. Type of eye-glasses
|\ |\ |\
C. Occlusion - CORRECT ANSWERS ✔✔A. Location
|\ |\ |\ |\ |\ |\
,You need to create a facial recognition solutions to identify named
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
employees. Which service should you use? |\ |\ |\ |\ |\
A. Azure AI Vision
|\ |\ |\
B. Azure AI Custom Vision
|\ |\ |\ |\ |\
C. Face - CORRECT ANSWERS ✔✔C. Face
|\ |\ |\ |\ |\ |\
You need to verify that the person in a photo taken at hospital
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
reception is the same person in a photo taken at a ward entrance 10
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
minutes later. What should you do? |\ |\ |\ |\ |\
A. Create a People Group and add a person for every hospital visitor
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
with multiple photographs to train a model
|\ |\ |\ |\ |\ |\ |\
B. Verify the face in the ward photo by comparing it to the detected
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
Face ID from the reception photo
|\ |\ |\ |\ |\
C. Compare the Age, head pose, and hair color for the faces in the
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
reception and ward photo's. - CORRECT ANSWERS ✔✔B. Verify
|\ |\ |\ |\ |\ |\ |\ |\ |\
the face in the ward photo by comparing it to the detected Face ID
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
from the reception photo
|\ |\ |\
Which API would be best for this scenario? You need to read a large
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
number of files with high accuracy. The Text is short sections of
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
handwritten text, some in English and some of it is in multiple |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
languages.
A. A custom Language API
|\ |\ |\ |\
B. Document Intelligence API
|\ |\ |\
, C. Image Analysis API - CORRECT ANSWERS ✔✔C. Image
|\ |\ |\ |\ |\ |\ |\ |\ |\
Analysis API |\
What levels of divisions are the OCR results returned?
|\ |\ |\ |\ |\ |\ |\ |\
A. Only total content and pages of text
|\ |\ |\ |\ |\ |\ |\
B. Blocks, words and lines of text
|\ |\ |\ |\ |\ |\
C. Total content, image tags, pages, words and lines of text -
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
CORRECT ANSWERS ✔✔B. Blocks, words and lines of text |\ |\ |\ |\ |\ |\ |\ |\
You've scanned a letter into PDF format and need to extract the text
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
it contains. What should you do?
|\ |\ |\ |\ |\
A. Use the Azure AI Custom Vision service
|\ |\ |\ |\ |\ |\ |\
B. Use the Image Analysis API of the Azure AI Vision service
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
C. Use the Document Intelligence API - CORRECT ANSWERS
|\ |\ |\ |\ |\ |\ |\ |\ |\
✔✔C. Use the Document Intelligence API
|\ |\ |\ |\ |\
You want Azure Video Indexer to analyze a video. What must you
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
do first?
|\
A. Use the Azure AI Vision service to extract key frames from the
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\ |\
video
B. Upload the video to Azure Video Indexer and index it
|\ |\ |\ |\ |\ |\ |\ |\ |\ |\
