Exam AI-102 All Questions

View all questions & answers for the AI-102 exam

Exam AI-102 topic 2 question 19 discussion

Actual exam question from Microsoft's AI-102

Question #: 19
Topic #: 2

HOTSPOT -
You are building an app that will enable users to upload images. The solution must meet the following requirements:
* Automatically suggest alt text for the images.
* Detect inappropriate images and block them.
* Minimize development effort.
You need to recommend a computer vision endpoint for each requirement.
What should you recommend? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Hot Area:

Show Suggested Answer

Suggested Answer:

by firewind at Sept. 22, 2022, 12:24 a.m.

Comments

Submit Cancel

Tanmay1178

Highly Voted 2 years, 1 month ago

I think it is vision/v3.2/analyze/?visualFeatures=Adult,Description for both

upvoted 38 times

...

zellck

Highly Voted 1 year, 6 months ago

1. https://westus.api.cognitive.microsoft.com/vision/v3.2/analyze/?visualFeatures=Adult,Description 2. https://westus.api.cognitive.microsoft.com/vision/v3.2/analyze/?visualFeatures=Adult,Description https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-describing-images Computer Vision can analyze an image and generate a human-readable phrase that describes its contents. The algorithm returns several descriptions based on different visual features, and each description is given a confidence score. The final output is a list of descriptions ordered from highest to lowest confidence.

upvoted 16 times

MeanJean

1 month, 3 weeks ago

This is a little tricky because Image Analysis 4.0 doesn't have an Adult feature but 3.2 does. And since it says with least development effort, I would agree that is would be https://westus.api.cognitive.microsoft.com/vision/v3.2/analyze/?visualFeatures=Adult,Description for both

upvoted 1 times

...

rdemontis

1 year, 2 months ago

thanks for explanation

upvoted 1 times

...

M25

1 year, 4 months ago

https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/use-case-alt-text?source=recommendations Alt text, or alternative text, is an HTML attribute added to the <img> tag that displays images on an application or web page. Alt text enables website owners to describe an image in plain text. These image descriptions improve accessibility by enabling screen readers such as Microsoft Narrator, JAWS, and NVDA to accurately communicate image content to their visually impaired and blind users. Alt text is also vital for image search engine optimization (SEO). It helps search engines understand the visual content in your images. The search engine is then better able to include and rank your website in search results when users search for the content in your website. Auto-generate alt text with Image Analysis: Image Analysis offers image captioning models that generate one-sentence descriptions of image visual content. Thank you @zellck!

upvoted 1 times

...

zellck

1 year, 6 months ago

https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-detecting-adult-content Computer Vision can detect adult material in images so that developers can restrict the display of these images in their software. Content flags are applied with a score between zero and one so developers can interpret the results according to their own preferences. You can detect adult content with the Analyze Image 3.2 API. When you add the value of Adult to the visualFeatures query parameter, the API returns three boolean properties—isAdultContent, isRacyContent, and isGoryContent—in its JSON response. The method also returns corresponding properties—adultScore, racyScore, and goreScore—which represent confidence scores between zero and one for each respective category.

upvoted 3 times

...

Load full discussion...

...

gyaansastra

Most Recent 4 months, 2 weeks ago

Generate Alt Text: https://westus.api.cognitive.microsoft.com/vision/v3.2/analyze/?visualFeatures=Adult,Descnption: Despite the spelling error, this endpoint is intended to generate descriptions for images, which can be used as alt text. Detect Inappropriate Content: https://westus.api.cognitive.microsoft.com/contentmoderator/moderate/v1.0/ProcessImage/Evaluate: This endpoint is specifically designed to detect and block inappropriate images using the Content Moderator API. Summary: Generate alt text: https://westus.api.cognitive.microsoft.com/vision/v3.2/analyze/?visualFeatures=Adult,Descnption Detect inappropriate content: https://westus.api.cognitive.microsoft.com/contentmoderator/moderate/v1.0/ProcessImage/Evaluate By using these endpoints, you can achieve the specified requirements while minimizing development effort.

upvoted 2 times

...

syupwsh

5 months ago

Adult,Description is CORRECT because this endpoint belongs to the Computer Vision API and includes the Description visual feature, which is used to automatically generate alt text for images. This minimizes development effort as it leverages pre-built capabilities of the Computer Vision API. Adult,Description is CORRECT because the Computer Vision API can detect adult content and generate human-readable phrases to describe the contents of an image. This endpoint allows you to analyze images for inappropriate content (using the Adult visual feature) while also providing descriptive captions (using the Description visual feature), fulfilling both requirements of detecting inappropriate images and minimizing development effort.

upvoted 1 times

...

NagaoShingo

7 months, 1 week ago

Adult Video

upvoted 1 times

...

taiwan_is_not_china

7 months, 2 weeks ago

Both will contain Adult,Description.

upvoted 2 times

...

takaimomoGcup

7 months, 3 weeks ago

Generate alt text should be "v3.2/analyze". Detect inappropriate content should be "v3.2/analyze".

upvoted 2 times

...

evangelist

11 months ago

description ==>Alt text

upvoted 2 times

...

propanther

1 year, 2 months ago

Both are https://westus.api.cognitive.microsoft.com/vision/v3.2/analyze/?visualFeatures=Adult,Description A string indicating what visual feature types to return. Multiple values should be comma-separated. Valid visual feature types include: Adult - detects if the image is pornographic in nature (depicts nudity or a sex act), or is gory (depicts extreme violence or blood). Sexually suggestive content (aka racy content) is also detected. Description - describes the image content with a complete sentence in supported languages. https://westus.dev.cognitive.microsoft.com/docs/services/computer-vision-v3-2/operations/56f91f2e778daf14a499f21b

upvoted 2 times

...

Tickxit

2 years, 3 months ago

I think it is two times /analyze/?visualFeatures=Adult,Description

upvoted 4 times

Anulf

2 years, 3 months ago

Shouldn't it be option 2 in the first column ? "iteratio"

upvoted 1 times

...

firewind

2 years, 3 months ago

Generate alt text can use either analyze or describe. From the given option, I think it should be the analyze url too. https://westcentralus.dev.cognitive.microsoft.com/docs/services/computer-vision-v3-2/operations/56f91f2e778daf14a499f21f

upvoted 2 times

Rob77

1 year, 8 months ago

Agreed, analyze in both answers

upvoted 1 times

...