Exam AI-102 All Questions

View all questions & answers for the AI-102 exam

Exam AI-102 topic 2 question 12 discussion

Actual exam question from Microsoft's AI-102

Question #: 12
Topic #: 2

DRAG DROP -
You are developing a call to the Face API. The call must find similar faces from an existing list named employeefaces. The employeefaces list contains 60,000 images.
How should you complete the body of the HTTP request? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
Select and Place:

Show Suggested Answer

Suggested Answer:

Box 1: LargeFaceListID -
LargeFaceList: Add a face to a specified large face list, up to 1,000,000 faces.
Note: Given query face's faceId, to search the similar-looking faces from a faceId array, a face list or a large face list. A "faceListId" is created by FaceList - Create containing persistedFaceIds that will not expire. And a "largeFaceListId" is created by LargeFaceList - Create containing persistedFaceIds that will also not expire.
Incorrect Answers:
Not "faceListId": Add a face to a specified face list, up to 1,000 faces.

Box 2: matchFace -
Find similar has two working modes, "matchPerson" and "matchFace". "matchPerson" is the default mode that it tries to find faces of the same person as possible by using internal same-person thresholds. It is useful to find a known person's other photos. Note that an empty list will be returned if no faces pass the internal thresholds. "matchFace" mode ignores same-person thresholds and returns ranked similar faces anyway, even the similarity is low. It can be used in the cases like searching celebrity-looking faces.
Reference:
https://docs.microsoft.com/en-us/rest/api/faceapi/face/findsimilar

by Jenny1 at June 16, 2021, 2:35 p.m.

Comments

Submit Cancel

Jenny1

Highly Voted 4 years ago

Correct.

upvoted 21 times

...

PHD_CHENG

Highly Voted 3 years, 1 month ago

Facelist ID up to 1,000 faces; LargeFaceListId up to 1,000,000 faces https://docs.microsoft.com/en-us/rest/api/faceapi/large-face-list

upvoted 13 times

...

syupwsh

Most Recent 3 months, 3 weeks ago

1. LargeFaceListId 2. matchFace https://learn.microsoft.com/en-us/rest/api/face/face/find-similar?view=rest-face-v1.0-preview&tabs=HTTP https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/use-large-scale

upvoted 1 times

...

gyaansastra

3 months, 4 weeks ago

Correct here is the Explanation: largefacelistid: Use this parameter because employeefaces contains 60,000 images, which exceeds the limit of a regular facelist. matchface: This mode is used to find similar faces. By using largefacelistid and matchface, you ensure that the Face API call can handle the large number of images in the list and find similar faces effectively.

upvoted 1 times

...

famco

9 months, 3 weeks ago

Another of the detective style finding answers from hidden clues in the english language usage. Microsoft is a truly remarkable org. Similar face, must find and employes. Similar face and Must find might point to matchFace, but for employees it should be matchPerson (we need the person not similar looking). Now, what will you choose? Very hard. Remarkable piece of hmm sweetness.

upvoted 2 times

famco

9 months, 3 weeks ago

And the fact that this remarkable org created a largeFaceList and a faceList and expects one to remember that piece of bad design. The size of the facelist should not be in the client calls, but at the server. Now if the facelist increases in size the clients need to change. What kind of org creates these kind of things and shamelessly ask that in certification exam. Microsoft is the answer.

upvoted 2 times

famco

9 months, 3 weeks ago

I will go for matchFace considering the other clue "similar face" instead of person. Man, this question should be taken to court and microsoft should be whipped

upvoted 1 times

...

rookiee1111

1 year ago

LargeFaceIdList matchFace - reason why not matchPerson - becomes matchPerson compares agains larger person group and not one to one, here we are doing matchFace to find similar faces based on one to one analysis.

upvoted 2 times

...

HaraTadahisa

1 year ago

1. LargeFaceListId 2. matchFace

upvoted 1 times

...

nanaw770

1 year ago

1. LargeFaceListId 2. matchFace

upvoted 1 times

...

varinder82

1 year, 3 months ago

Final Answer: 1. LargeFaceListId 2. matchFace ( matchPerson could return an empty list, but matchFace will not.)

upvoted 4 times

...

Ody

1 year, 3 months ago

The key is "must find". matchPerson could return an empty list, but matchFace will not.

upvoted 1 times

...

rdemontis

1 year, 7 months ago

correct answer: https://learn.microsoft.com/en-us/rest/api/faceapi/face-list?view=rest-faceapi-v1.0

upvoted 1 times

rdemontis

1 year, 7 months ago

Sorry but I have to laugh off my previous answer: "matchPerson" is the default mode that it tries to find faces of the same person as possible by using internal same-person thresholds. It is useful to find a known person's other photos. Note that an empty list will be returned if no faces pass the internal thresholds. "matchFace" mode ignores same-person thresholds and returns ranked similar faces anyway, even the similarity is low. It can be used in the cases like searching celebrity-looking faces" https://learn.microsoft.com/en-us/rest/api/faceapi/face/find-similar?view=rest-faceapi-v1.0&tabs=HTTP

upvoted 1 times

rdemontis

1 year, 7 months ago

in this case we are talking about finding the faces of people who are employees of an organization. We are not talking about famous people. So the recognition will have to be done by an internal set of images of the faces whose faces are to be matched in the corporate photo gallery. Also set maxNumOfCandidatesReturned = 1. Which means that it is also acceptable not to find matches. Which is not the case with matchFace because it also tolerates a low confidence coefficient. Considering what is reported in the article I think the second answer to the question is more correct matchParson.

upvoted 2 times

rdemontis

1 year, 7 months ago

Sorry, but after further investigation I am not sure that this is the case. Frankly, the Microsoft documentation in this case doesn't seem to be very satisfactory.

upvoted 1 times

famco

9 months, 3 weeks ago

Although Microsoft is known for bad products, confusing naming conventions, no-alignment across products, confusing documentation and useless certification questions, this is a case of wrong question.

upvoted 1 times

...

Eltooth

2 years, 11 months ago

I'm leaning towards: largeFaceListId and matchedPerson https://docs.microsoft.com/en-us/rest/api/faceapi/face/find-similar?tabs=HTTP#find-similar-results-example "matchPerson" is the default mode that it tries to find faces of the same person as possible by using internal same-person thresholds. It is useful to find a known person's other photos. Note that an empty list will be returned if no faces pass the internal thresholds. "matchFace" mode ignores same-person thresholds and returns ranked similar faces anyway, even the similarity is low. It can be used in the cases like searching celebrity-looking faces.

upvoted 8 times

makciek

1 year, 10 months ago

it says "The call must find similar faces from an existing list named employeefaces", similar being the keyword here so matchFace i think is correct.

upvoted 1 times

...

ccie_pgh

1 year, 5 months ago

Agree since code also has "maxNumOfCandidatesReturned", which would be ignored by "matchFace"... both "matchFace" and "matchPerson" find similars but only "matchPerson" will use internal thresholds.

upvoted 2 times

...

PHD_CHENG

3 years ago

Was on exam 7 Jun 2022

upvoted 3 times

...

luishenriquesb

3 years ago

it's should be largeFaceListId not LargeFaceListId (Capitalized). It's wouldn't work in a http request...

upvoted 5 times

...

gursimran_s

3 years, 2 months ago

The 1000 face parameter is for the faceIds and not the faceListId.So, it could be faceListId as well.

upvoted 1 times

...

gursimran_s

3 years, 2 months ago

Why not faceListId? Nothing specific mentioned on MS docs.

upvoted 1 times

...

klion

3 years, 4 months ago

"matchPerson" Find similar results example Sample Request HTTP POST {Endpoint}/face/v1.0/findsimilars Ocp-Apim-Subscription-Key: {API key} Request Body JSON { "faceId": "c5c24a82-6845-4031-9d5d-978df9175426", "largeFaceListId": "sample_list", "maxNumOfCandidatesReturned": 1, "mode": "matchPerson" } https://docs.microsoft.com/en-us/rest/api/faceapi/face/find-similar

upvoted 3 times

...

Load full discussion...