combined_Fundamentals of optical character recognition_study guide Flashcards

1
Q

What is the primary intersection of AI fields that enables OCR capabilities?

A

The primary intersection of AI fields is computer vision and natural language processing, where vision capabilities ‘read’ the text, and natural language processing makes sense of it.

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

Describe the core function of machine learning models in the context of OCR.

A

Machine learning models in OCR are trained to recognize individual shapes as letters, numerals, punctuation, or other elements of text.

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

What is the Azure AI Vision service’s Read API and what is it optimized for?

A

The Read API is Azure AI Vision’s OCR engine that powers text extraction from images, PDFs, and TIFF files, and it is optimized for general, non-document images.

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

Explain the three-level hierarchy of results returned by the Read API.

A

The Read API returns results arranged into a hierarchy of pages, lines within pages, and words within lines, each with bounding box coordinates and text.

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

What are the two resource types you can create in Azure for using Azure AI Vision?

A

The two resource types are a specific Azure AI Vision resource and a general Azure AI services resource that includes Azure AI Vision along with other AI services.

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

What are three ways you can use the Azure AI Vision Read API?

A

You can use the Azure AI Vision Read API through the Vision Studio, REST API, or Software Development Kits (SDKs) like Python, C#, and JavaScript.

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

What is the primary benefit of using Azure AI Vision Studio for OCR tasks?

A

Azure AI Vision Studio provides a graphical user interface for using the Read API without requiring any coding to get started.

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

How can you access the OCR engine within Vision Studio?

A

The OCR engine can be accessed by selecting ‘Optical Character Recognition’ and the ‘Extract text from images’ tile in Vision Studio.

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

What type of data format are the raw results of the OCR analysis returned in?

A

The raw results are returned in JSON format which includes bounding box locations on the page and the detected text.

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

Besides speed and efficiency, what is one other key benefit of automating text processing using OCR?

A

Automating text processing with OCR improves speed, efficiency and also removes the need for manual data entry, freeing up resources for more important tasks.

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