AI-102 Question 121
Single answerYou are designing a solution to extract text from scanned invoices for your company using Azure AI Vision. The invoices include handwritten notes and printed text in various fonts. You need to ensure the solution can handle both types of text effectively. Which Azure AI Vision feature should you use to achieve this?
- A
Read API
- B
OCR API
- C
Custom Vision
- D
Form Recognizer
Show answer and explanation
Correct answer: A
Explanation
The Read API is part of Azure AI Vision and is optimized for extracting both printed and handwritten text from images and documents. It is a modern replacement for the older OCR API and is suitable for use cases like extracting text from scanned invoices where both handwriting and printed text are present.
- A. Correct.
The Read API is specifically designed to extract both printed and handwritten text from images and documents, making it the best choice for this scenario.
- B. Incorrect.
The OCR API is an older technology that focuses primarily on printed text and may not handle handwritten text as effectively as the Read API.
- C. Incorrect.
Custom Vision is used for training models for custom image classification or object detection, not text extraction.
- D. Incorrect.
Form Recognizer is used for structured document analysis and extracting key-value pairs or table data, but it is not directly optimized for extracting general text from images.