Microsoft Azure AI Fundamentals (AI-900) Practice Exam

Optical character recognition (OCR) is the most suitable type of computer vision for developing a mobile app that enables employees to scan and store their travel expenses. OCR technology is designed to recognize and convert text from images into machine-readable format. This capability allows users to take photographs of receipts, invoices, or any documentation containing expenses, and automatically extract relevant financial data such as amounts, dates, and merchant information.

Using OCR in this context streamlines the expense-reporting process and eliminates the need for manual data entry, enhancing efficiency and reducing errors. The app can instantly convert scanned images of receipts into structured data, making it easier for employees to track and manage their expenses.

In contrast, facial recognition is aimed at identifying or verifying individuals based on their facial features, which does not apply to the task of scanning travel expenses. Image classification involves categorizing images into predefined classes but does not specifically handle text extraction. Semantic segmentation is about partitioning an image into segments that correspond to objects or regions, which is unnecessary for the task at hand. Each of these other options serves a different purpose and does not align with the goal of extracting textual information from expense documentation.