Skip to Content

AI-900: How to use the Read API to extract text from images and documents

Learn how the Read API in Azure Cognitive Services can process single-page and multi-page documents and return a JSON response with the recognized text and its location in the original image.

Question

When you use the Read API to process an image, what hierarchy of information does it return?

A. First pages, then lines, then words
B. First words, then lines, then pages
C. First lines, then pages, then words

Answer

A. First pages, then lines, then words

Explanation

The results from the Read API are arranged into the following hierarchy: first pages, then lines, then words.

The correct answer is A. First pages, then lines, then words.

The Read API is a part of the Computer Vision service in Azure Cognitive Services that can extract printed and handwritten text from images and documents. The Read API can process both single-page and multi-page documents and return a JSON response that contains the recognized text and its location in the original image. The JSON response has a hierarchy of information that reflects the structure of the document. The hierarchy is as follows:

  • The top level is the readResult, which contains information about the document, such as the language, the angle of rotation, and the number of pages.
  • The next level is the pageResult, which contains information about each page in the document, such as the page number, the width and height of the page, and the unit of measurement.
  • The next level is the line, which contains information about each line of text in the page, such as the text content, the bounding box coordinates, and the confidence score.
  • The lowest level is the word, which contains information about each word in the line, such as the text content, the bounding box coordinates, and the confidence score.

The Read API returns the information in this hierarchy to preserve the layout and formatting of the original document and to enable the user to reconstruct the document from the extracted text. For example, the user can use the page number, the angle of rotation, and the bounding box coordinates to place the text in the correct position and orientation on the page. The user can also use the line and word information to identify the paragraphs, headings, lists, tables, and other elements in the document.

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump

Alex Lim is a certified IT Technical Support Architect with over 15 years of experience in designing, implementing, and troubleshooting complex IT systems and networks. He has worked for leading IT companies, such as Microsoft, IBM, and Cisco, providing technical support and solutions to clients across various industries and sectors. Alex has a bachelor’s degree in computer science from the National University of Singapore and a master’s degree in information security from the Massachusetts Institute of Technology. He is also the author of several best-selling books on IT technical support, such as The IT Technical Support Handbook and Troubleshooting IT Systems and Networks. Alex lives in Bandar, Johore, Malaysia with his wife and two chilrdren. You can reach him at [email protected] or follow him on Website | Twitter | Facebook

    Ads Blocker Image Powered by Code Help Pro

    Your Support Matters...

    We run an independent site that is committed to delivering valuable content, but it comes with its challenges. Many of our readers use ad blockers, causing our advertising revenue to decline. Unlike some websites, we have not implemented paywalls to restrict access. Your support can make a significant difference. If you find this website useful and choose to support us, it would greatly secure our future. We appreciate your help. If you are currently using an ad blocker, please consider disabling it for our site. Thank you for your understanding and support.