Image and video processing solutions 15-20% Flashcards

1
Q

Face app capabilities

A

identify, verify, find similar, group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the capabilities of the computer vision app?

A

Image analysis, Video analysis, Image classification, object detection, facial analysis

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are the different face detection models?

A

detection_01, detection_02, detection_03

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What’s good about detection_02?

A

It has improved accuracy on small, side-view, and blurry faces, but it won’t return attributes or landmarks

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What’s good about detection_03?

A

Better accuracy on small faces than 02, and will return attributes and landmarks

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What computer vision tier supports OCR?

A

S2

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Which document formats does form recognizer prebuilt read?

A

PDF, word, and excel

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What does A1 and A2 mean in the image classification domain?

A

Improved accuracy

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

what formats can OCR read api ingest?

A

jpeg, png, bmp, pdf, and tiff

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

How many pages can PDFs and TIFFs be for OCR read api?

A

2000 pages, first 2 pages for free tier

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

How large can the image files be for the OCR read api?

A

<500MB, 4MB for the free tier

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What are the image dimensions for the OCR read api?

A

50^2 to 10,000^2

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

How many print languages can the OCR read api handle?

A

164

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

How many handwritten languages can the OCR read api handle?

A

9

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

How does calling the OCR read api work?

A

You call it first and receive an async ID. You then call again for the results

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How to set up Conversational language understanding(CLU)?

A

Using intents as goals and utterances as signals for those goals. Entities provide specification.

17
Q

What are the three types of entities in a conversational language understanding?

A

learned entities, list entities, prebuilt entities

18
Q

single label vs multi label

A

Single - one item can have one label, multi - one item can have multiple labels

19
Q

what do you need to prepare for question answering?

A

A knowledge base to pull from