AI-900 Question 176
Single answerA company wants to automate the process of extracting text from scanned invoices and identifying specific fields such as 'Invoice Number' and 'Total Amount'. Which capability of Azure AI Vision would be most suitable for this scenario?
- A
Optical Character Recognition (OCR)
- B
Content Moderation
- C
Image Classification
- D
Facial Recognition
Show answer and explanation
Correct answer: A
Explanation
Azure AI Vision's OCR capability is designed to extract text from images or scanned documents, making it highly suitable for automating tasks such as reading and processing invoices. It can recognize text and extract specific fields like 'Invoice Number' or 'Total Amount'. Other options, like Content Moderation, Image Classification, and Facial Recognition, are unrelated to this scenario.
- A. Correct.
Optical Character Recognition (OCR) is the correct capability for extracting text from images or documents, such as scanned invoices. It allows for the detection and recognition of printed or handwritten text.
- B. Incorrect.
Content Moderation is focused on identifying inappropriate or harmful content in images or videos, which is unrelated to the requirement of extracting text from invoices.
- C. Incorrect.
Image Classification is used to categorize images into predefined groups, but it does not involve extracting specific text or fields from images.
- D. Incorrect.
Facial Recognition is used to detect and analyze faces in images, which is unrelated to extracting text or fields from invoices.