Learn about the minimum image size recommended for using a custom model with Form Recognizer, a service that extracts information from forms and documents.
Table of Contents
Question
When using a custom model with Form Recognizer, what is the minimum image size recommended?
A. 40×40 pixels
B. 50×50 pixels
C. 30×30 pixels
Answer
B. 50×50 pixels
Explanation
The correct answer is B. 50×50 pixels. This is the minimum image size recommended for using a custom model with Form Recognizer, according to the official documentation. A custom model is a machine learning model that is trained on a set of labeled or unlabeled documents to extract information specific to your business needs. Custom models can handle structured, semi-structured, or unstructured forms and documents, such as invoices, receipts, contracts, etc.
To create a custom model, you need to provide a dataset of documents that have a minimum image size of 50×50 pixels and a maximum file size of 20 MB per page. The documents can be in PDF, JPEG, PNG, or TIFF format. You can use the Form Recognizer Studio, a web application that simplifies the creation and training of custom models, or the Form Recognizer REST API, a programmatic interface that allows you to interact with the service.
The image size is important for the custom model to be able to detect and extract the text, key-value pairs, tables, and other elements from the documents. If the image size is too small, the model may not be able to recognize the text or the layout of the document. If the image size is too large, the model may take longer to process the document or exceed the file size limit. Therefore, it is recommended to use an image size that is clear and readable, but not too large or too small.
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.
