You are working on building an application that can extract text from handwritten (English only) and printed text, text-heavy images and multi-page PDF.
Which of the below listed should you use?
Click on the arrows to vote for the correct answer
A. B. C. D.Correct Answer:D.
Option A is INCORRECT.
Computer Vision Analyze Image API does not perform OCR and text extraction.
Computer Vision Analyze Image API can perform below amongst others.
- Object detection
- Brand detection
- Image Categorization
- Image description Option B is INCORRECT.
Custom Vision does not perform OCR and Text extraction.
Option C is INCORRECT.
Content Moderator performs the moderation of the content and facilitates human review tools for videos, text and images.
Content moderator does not perform OCR and text extraction.
Option D is CORRECT.
Azure's latest OCR technology, Computer Vision Read API, can be used for the purpose of text-extraction from handwritten (English only) and printed text, text-heavy images and multi-page PDF.References:
Based on the requirement to extract text from handwritten and printed text, text-heavy images, and multi-page PDFs, the most appropriate API to use is the Computer Vision Read API (option D).
Here's why:
Computer Vision Analyze Image API (option A): This API can detect and extract printed text from images, but it cannot extract text from handwritten text or multi-page PDFs.
Custom Vision API (option B): This API is used for image classification and object detection, but it cannot extract text from images or PDFs.
Content Moderator (option C): This API is used for detecting and moderating inappropriate content in text, images, and videos, but it cannot extract text from images or PDFs.
Computer Vision Read API (option D): This API can extract printed and handwritten text from images and multi-page PDFs. It uses Optical Character Recognition (OCR) technology to extract text accurately. It can also extract text from images with low quality, distorted or tilted text, and multi-column layouts.
In summary, the Computer Vision Read API (option D) is the most appropriate API to use for extracting text from handwritten and printed text, text-heavy images, and multi-page PDFs.