WorksheetsOCR & FR
Total questions: 10
Worksheet time: 20mins
What are some examples of how Optical Character Recognition could be used in real world applications? Select all that apply.
Extract text from bills and invoices
Transcribe text from one script to another (e.g. Japanese script to Latin script)
Extract text from product
Extract words from audio files
What two APIs does Computer Vision offer for reading text?
The OCR API
The Read API
The Language Reader API
The Text API
What is one reason why an intake desk might want to use the Form Recognizer service instead of manually re-entering data from intake forms?
Form Recognizer services can replace people at intake desks, reducing the cost of running a business.
Form Recognizer services provide the building blocks for automation by using intelligent services to extract data at scale
Form Recognizer should only be used on typed forms, and so wouldn’t be useful at an intake desk.
Form Recognizer services will not make mistakes that are often made by humans when re-entering data manually.
What is an example of how the Business Cards prebuilt Form Recognizer model could be used?
Processing paperwork for each card owner in real time.
Automatically creating contacts from images to integrate data with a CRM
Analyzing consumer behavior with business card drop offs
Improving business card design through comparisons of collected cards.
Which API would be best for this scenario? You need to read a large amount of text with high accuracy. Some of the text is handwritten in English and some of it is printed in multiple languages.
OCR API
Read API
Image Analysis API
What is a difference between the response from the Read API versus the OCR API?
There's no difference between the response returned, the only difference is that the Read API can be used for handwritten text.
The OCR API results break down by region, line, then word, while the Read API results break down by page, then line, and then word.
The OCR API results include bounding box coordinates for images and text, while the Read API results only include results for text.
You have scanned a letter into PDF format and need to extract the text it contains. What should you do?
Use the Custom Vision service
Use the OCR API of the Computer Vision service.
Use the Read API of the Computer Vision service.
A person plans to use a Form Recognizer prebuilt invoice model. To extract form data using the model, what are two calls they need to make to the REST API?
Train Model and Get Model Labels
Analyze Invoice and Get Analyze Invoice Result
Create Form Recognizer and Get Analyze Invoice Result
A person needs to build an application that submits expense claims and extracts the merchant, date, and total from scanned receipts. What's the best way to do this?
Use the Read API of the Computer Vision service.
Use Form Recognizer's prebuilt receipts model
Use Form Recognizer's Layout service
A person is building a custom model with Form Recognizer services. What is a difference between their supervised and unsupervised training processes?
Unsupervised training requires form images while supervised training requires form images and additional .json files.
When they store training forms in an Azure storage container, they need to generate a SAS URL for the container for unsupervised training but not for supervised training.
Unsupervised training produces a model ID while supervised training produces labeled JSON files.
