Microsoft Exam AI-102 Topic 8 Question 55 Discussion

Actual exam question for Microsoft's AI-102 exam

Question #: 55
Topic #: 8

You have an Azure Cognitive Search solution and a collection of handwritten letters stored as JPEG files.

You plan to index the collection. The solution must ensure that queries can be performed on the contents of the letters.

You need to create an indexer that has a skillset.

Which skill should you include?

Akey phrase extraction

Boptical character recognition (OCR)

Cdocument extraction

Dimage analysis

Show Suggested Answer

Suggested Answer: B

by Vi at Dec 23, 2023, 07:37 AM

Limited Time Offer

25%

Off

Get Premium AI-102 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Slyvia

8 months ago

Haha, good point! What if the letters were written by a bunch of five-year-olds? We'd need some serious handwriting deciphering skills to make sense of that. But I think OCR is still the way to go - it's the industry standard for this kind of task.

upvoted 0 times

...

Torie

8 months ago

Exactly, OCR is the skill we need to convert those handwritten letters into searchable text. I can't imagine trying to query the letters without that capability. Although, I do wonder if the letters will all be perfectly legible. Maybe we should also include some kind of handwriting recognition just in case.

upvoted 0 times

Hyman

7 months ago

I think that's a great idea, especially if some of the letters are not perfectly legible.

upvoted 0 times

...

Chau

7 months ago

What do you think about including handwriting recognition as an additional skill to ensure accuracy?

upvoted 0 times

...

Nydia

8 months ago

D) image analysis

upvoted 0 times

...

Jaleesa

8 months ago

I agree, including OCR is essential for converting the handwritten letters into searchable text.

upvoted 0 times

...

Garry

8 months ago

A) key phrase extraction

upvoted 0 times

...

Hillary

8 months ago

C) document extraction

upvoted 0 times

...

Tiffiny

8 months ago

B) optical character recognition (OCR)

upvoted 0 times

...

Maryrose

8 months ago

I agree, OCR is definitely the way to go. The other options don't seem relevant - key phrase extraction and document extraction are more for structured data, and image analysis would give us information about the images themselves, but not the actual content we're interested in.

upvoted 0 times

...

Ashlyn

8 months ago

Alright, let's think this through. We need an indexer that can handle handwritten letters stored as JPEG files, and the solution must allow queries to be performed on the contents of the letters. That means we need to extract the text from the images, so I think the obvious choice here is optical character recognition (OCR).

upvoted 0 times

...