Exam AI-102 topic 2 question 22 discussion

I think that the answers are wrong. They should be: 1 - Computer Vision analyze image 2 - imageType According to https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-detecting-image-types Computer Vision can analyze the content type of images, indicating whether an image is clip art or a line drawing

1. Computer Vision analyze images 2. imageType https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-detecting-image-types With the Analyze Image API, Computer Vision can analyze the content type of images, indicating whether an image is clip art or a line drawing.

Service Endpoint: a. Computer Vision analyze images This endpoint provides comprehensive analysis of images, including categorization. Property: c. imageType This property can be used to identify whether an image is a photograph, drawing, or clipart. Summary: Service endpoint: Computer Vision analyze images Property: imageType By using the Computer Vision analyze images endpoint with the imageType property, we can effectively tag the images as photographs, drawings, or clipart.

Computer Vision analyze images is CORRECT because this endpoint provides a variety of features for analyzing images, including categorization into types such as photographs, drawings, or clipart. It is well-suited for tagging large libraries of images with general descriptive tags. imageType is CORRECT because this property provides information about the type of image, such as whether it is a photograph, drawing, or clipart. This property is specifically designed to categorize the visual style or format of the image.

first is - Computer Vision analyze images 2nd - imageType info here - https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-detecting-image-types

1. Computer Vision analyze images 2. imageType

1. Computer Vision analyze images 2. imageType

The following aligned answer is correct. 1. Computer Vision analyze images 2. imageType

1. Computer Vision analyze images 2. imageType

Service endpoint should be "Computer Vision analyze images". Property should be "imageType".

Service endpoint shoud be "Computer Vision analyze images". Property should be "imageType".

Appeared on Oct/29/2023.

I would say the answers are correct. Image type can only indicate whether an image is clip art or a line drawing. It can’t tell you if it’s a photograph or not - you can’t just assume that if the image isn’t a clip art or a line drawing will automatically be categorized as a photograph. It’s a very sloppy solution IMO. Besides you have thousands of images and it’s a good reason to create your own model.

To tag images as photographs, drawings, or clipart, you should use the following service endpoint and response property: Service endpoint: Computer Vision image classification Property: imageType The Computer Vision image classification endpoint allows you to classify images into different categories, and the imageType property specifically provides information about the type of image, such as whether it is a photograph, drawing, or clipart.

ChatGPT: You can use the Microsoft Azure Computer Vision API to tag the images as photographs, drawings, or clipart. You can call the "Describe Image" API endpoint and use the "imageType" property of the response to determine if the image is a photograph, a drawing, or clipart. The "imageType" property can have the following values: "Clipart": Indicates that the image is a clipart. "LineDrawing": Indicates that the image is a line drawing. "Photograph": Indicates that the image is a photograph. You can send an HTTP POST request to the API endpoint with the image file as the request body and specify the "imageType" in the "visualFeatures" parameter. The API will return a JSON response containing the "imageType" property along with other properties such as "tags", "description", and "categories".