Exam AI-102 All Questions

View all questions & answers for the AI-102 exam

Exam AI-102 topic 2 question 34 discussion

Actual exam question from Microsoft's AI-102

Question #: 34
Topic #: 2

HOTSPOT
-

You are building an app that will share user images.

You need to configure the app to meet the following requirements:

• Uploaded images must be scanned and any text must be extracted from the images.
• Extracted text must be analyzed for the presence of profane language.
• The solution must minimize development effort.

What should you use for each requirement? To answer, select the appropriate options in the answer area.

NOTE: Each correct selection is worth one point.

Show Suggested Answer

Suggested Answer:

by audlindr at Feb. 29, 2024, 6:27 p.m.

Comments

Submit Cancel

Murtuza

Highly Voted 1 year, 3 months ago

Text Extraction from Images: You can use an Optical Character Recognition (OCR) service to scan and extract text from the uploaded images. Computer Vision API are examples of services that provide OCR capabilities. Profanity Check: Once the text is extracted, you can use a text analytics service to analyze the presence of profane language. Services Content Moderator API can help identify and filter out inappropriate content.

upvoted 10 times

aa18a1a

9 months ago

Agree with this answer. Take a look at this small blurb on this portion of the Microsoft docs: https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-ocr?view=doc-intel-4.0.0 "If you want to extract text from PDFs, Office files, or HTML documents and document images, use the Document Intelligence Read OCR model. It's optimized for text-heavy digital and scanned documents..." There's nowhere in this question that states these images will be "document images". Despite the fact that document intelligence CAN accept images, I've received no indication that we should assume these images will be documents.

upvoted 1 times

...

haby

Highly Voted 1 year, 1 month ago

Azure AI vision for me. Both Document Intelligence and AI vision have OCR, but document inte is more for structure and semi-structure files, like pdf doc, w-2, forms, etc. AI vision is easier to extract simple text from general images.

upvoted 6 times

...

gyaansastra

Most Recent 4 months, 2 weeks ago

Text Extraction: Azure AI Computer Vision: This service can effectively extract text from images using OCR (Optical Character Recognition). Profane Language Detection: Content Moderator: This service is designed to analyze text for the presence of profane language and other inappropriate content.

upvoted 3 times

...

syupwsh

5 months ago

Azure AI Computer Vision is CORRECT because it provides OCR (Optical Character Recognition) capabilities for extracting text from general-purpose images, such as photographs, which aligns with the text extraction requirement for uploaded user images. While it is not optimized for structured documents, it works well for unstructured, general image scenarios, making it suitable for this use case if the type of images is unspecified. Content Moderator is CORRECT because it is specifically designed to detect harmful or inappropriate content, including profanity, in both text and images. It provides robust text moderation capabilities, which can analyze the extracted text from images and identify profane language effectively. This solution minimizes development effort as it directly addresses the requirement for profanity detection.

upvoted 1 times

...

anto69

11 months, 2 weeks ago

Text extraction: Azure AI Document Intelligence Profane language detection: Content Moderator (now Azure AI Content Safety)

upvoted 3 times

...

rookiee1111

1 year ago

Azure AI Computer Vision has ReadApi for OCR feature to extract text from images, and content moderator for removing anything profane

upvoted 2 times

rookiee1111

1 year ago

Azure AI Document Intelligence (formerly Form Recognizer): Purpose: Specialized document analysis. Capabilities: Advanced OCR to extract text, key-value pairs, and table data from documents. Customizable models to extract structured data from forms and invoices. Tailored for processing documents such as forms, receipts, invoices, business cards, and other structured documents. Here we are dealing with scanned images

upvoted 1 times

...

NagaoShingo

1 year, 1 month ago

1. Azure AI Document Intelligence 2. Content Moderator

upvoted 1 times

Toby86

1 year ago

We're looking at Images, not documents. And if the images contained documents, we don't know that from the question. Answer is correct

upvoted 3 times

mrg998

10 months ago

agree, they have not said if the images will be images of documents or not. it could be images of anything that we need to extract from

upvoted 1 times

...

takaimomoGcup

1 year, 1 month ago

1. Azure AI Document Intelligence 2. Content Moderator

upvoted 1 times

...

funny_penguin

1 year, 1 month ago

on exam but with AI Content Safety instead of content moderator. For the first, I chose Azure AI Document Intelligence

upvoted 1 times

...

ShardulShende

1 year, 2 months ago

Why not Azure AI Document Intelligence for the first option?

upvoted 2 times

ShardulShende

1 year, 2 months ago

Should be Azure AI Document Intelligence. Document Intelligence Read Optical Character Recognition (OCR) model runs at a higher resolution than Azure AI Vision Read and extracts print and handwritten text from PDF documents and scanned images. https://learn.microsoft.com/en-us/answers/questions/1512283/vision-studio-vs-document-intelligence-studio-ocr

upvoted 1 times

...

audlindr

1 year, 4 months ago

I hope the Questions are revisited by Microsoft. Why would there be a question on deprecated services https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/overview Azure Content Moderator is being deprecated in February 2024, and will be retired by February 2027. It is being replaced by Azure AI Content Safety, which offers advanced AI features and enhanced performance.

upvoted 4 times

...