AI-102 Question 122
Single answerYou are developing an application that needs to extract text from scanned invoices and receipts in various file formats, such as JPEG, PNG, and PDF. The text extraction process should support multi-language recognition and handwritten text. Which Azure service or feature should you use to achieve this?
- A
Azure AI Vision's Optical Character Recognition (OCR) feature
- B
Azure Cognitive Search
- C
Azure Form Recognizer
- D
Azure Translator
Show answer and explanation
Correct answer: A
Explanation
Azure AI Vision's OCR feature provides the capability to extract text from images and documents in various formats, supporting multi-language recognition and handwritten text. This makes it the most suitable choice for scenarios requiring text extraction from scanned invoices and receipts.
- A. Correct.
Azure AI Vision's Optical Character Recognition (OCR) feature is specifically designed to extract text from images and documents, including support for multi-language recognition and handwritten text. This is the correct choice for this scenario.
- B. Incorrect.
Azure Cognitive Search enables search capabilities over structured or unstructured data, but it is not designed for extracting text from images or documents.
- C. Incorrect.
Azure Form Recognizer is used for extracting key-value pairs and structured data from forms and invoices, but it is not intended for general-purpose text extraction from images or handwritten text.
- D. Incorrect.
Azure Translator is used for translating text between different languages, but it does not provide functionality for text extraction from images or documents.