Match the facial recognition tasks to the appropriate questions. To answer, drag the appropriate task from the column on the left to its question on the right. Each task may be used once, more than once, or not at all. NOTE: Each correct selection is worth one point.
Which metric can you use to evaluate a classification model?
Correct Answer: A
What does a good model look like? An ROC curve that approaches the top left corner with 100% true positive rate and 0% false positive rate will be the best model. A random model would display as a flat line from the bottom left to the top right corner. Worse than random would dip below the y=x line. Reference: https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#classification
Question 5
You are building a tool that will process images from retail stores and identify the products of competitors. The solution will use a custom model. Which Azure Cognitive Services service should you use?
Correct Answer: A
to 300 words in Explanation: The Custom Vision service under Azure Cognitive Services is specifically designed for image classification and object detection tasks that require a custom-trained model. According to the AI-900 official study materials, Custom Vision enables developers to "build, deploy, and improve image classifiers that recognize specific objects in images based on custom data." In this question, the goal is to build a system that processes images from retail stores and identifies products of competitors. Since these are unique products that may not be part of Microsoft's pre-trained models, a custom model must be created. The Custom Vision service allows you to upload your own labeled images (e. g., product pictures), train a model to recognize those products, and then deploy it as an API for image recognition tasks. Other options explained: * B. Form Recognizer is used to extract text, key-value pairs, and tables from structured or semi- structured documents like invoices or receipts. It is not suitable for object identification. * C. Face service detects and analyzes human faces, providing attributes like age, emotion, and facial landmarks, but cannot recognize general objects like products. * D. Computer Vision is a general-purpose image analysis service used for tagging, OCR, and scene recognition, but it uses pre-trained models. It doesn't allow for custom product identification. Thus, based on Microsoft's guidance, the best fit for recognizing competitor products from images using a custom-trained model is A. Custom Vision.
