Exam AI-900 topic 1 question 186 discussion

Analysis. Used in computer vision

Analysis is correct answer

It is Analysis - as it involves evaluating facial features and characteristics to provide insights, such as feedback on exposure, noise, and occlusion in portrait photography.

Analysis

Detection, because: Attributes are a set of features that can optionally be detected by the Detect API. The following attributes can be detected: Accessories: Indicates whether the given face has accessories. This attribute returns possible accessories including headwear, glasses, and mask, with a confidence score between zero and one for each accessory. ***** Blur: Indicates the blurriness of the face in the image. This attribute returns a value between zero and one and an informal rating of low, medium, or high. ***** Exposure: Indicates the exposure of the face in the image. This attribute returns a value between zero and one and an informal rating of underExposure, goodExposure, or overExposure. https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-face-detection

Answer is correct. Counterintuitively, it is not face analysis, but face detection. Face analysis was used for things like inferring emotional states, age gender, etc, but it was retired to prevent stereotyping, discrimination, etc. Face detection service provides hints about exposure and so on.

It falls under Detection. Look at Face API ref https://westus.dev.cognitive.microsoft.com/docs/services/563879b61984550e40cbbe8d/operations/563879b61984550f30395236 Face - Detect "Optional parameters include faceId, landmarks, and attributes. Attributes include headPose, glasses, occlusion, accessories, blur, exposure, noise, mask, and qualityForRecognition."

An AI solution that assists photographers in capturing improved portrait photographs by offering feedback on exposure, noise, and occlusion falls under the category of facial analysis. This technology evaluates various aspects of the subject’s face and provides insights to enhance the overall quality of the portrait. It doesn’t focus on recognizing specific individuals (as in face recognition) or merely detecting faces (as in face detection)

Analysis

In my opinion the answer is Detection. https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-identity#face-detection-and-analysis The above states that "face detection can extract a set of face-related attributes, such as head pose, age, emotion, facial hair, and glasses". For me, analysis is more the facial expression and emotion. e.g. are the people in the photo looking annoyed, upset etc. rather than the physical quality of the photo, which the detection service would be better at providing feedback on

Analysis

The Al solution described is an example of facial analysis. Facial analysis involves extracting information and insights about a person's face, such as their expression, age, gender, or other characteristics. The solution described uses facial analysis to evaluate various aspects of portrait photographs, such as exposure, noise, and occlusion, to provide feedback to the photographer on how to improve the quality of their portraits. Facial detection is the task of locating and identifying the presence of faces within an image or video, while facial recognition is the process of identifying or verifying a person's identity based on their facial features. These tasks are related to facial analysis but are not the primary focus of the solution described. Therefore, the Al solution that provides feedback on portrait photographs based on exposure, noise, and occlusion is an example of facial analysis, which involves extracting information about a person's face to gain insights and evaluate various characteristics.

An AI solution that helps photographers take better portrait photographs by providing feedback on exposure, noise, and occlusion is an example of facial analysis or facial assessment. Facial analysis involves the use of computer vision and machine learning techniques to analyze and interpret facial features and characteristics. In this case, the AI solution would analyze the subject's face in the photograph to provide feedback on exposure (ensuring proper lighting and tonal range), noise (evaluating image quality and reducing unwanted artifacts), and occlusion (identifying any obstructions or distractions on the subject's face). By leveraging AI-powered facial analysis, photographers can receive valuable insights and recommendations to improve the overall quality of their portrait photographs.

Azure AI Face can return the rectangle coordinates for any human faces that are found in an image, as well as a series of attributes related to those faces such as: • Blur: how blurred the face is (which can be an indication of how likely the face is to be the main focus of the image) • Exposure: aspects such as underexposed or over exposed and applies to the face in the image and not the overall image exposure • Glasses: if the person is wearing glasses • Head pose: the face's orientation in a 3D space • Noise: refers to visual noise in the image. If you have taken a photo with a high ISO setting for darker settings, you would notice this noise in the image. The image looks grainy or full of tiny dots that make the image less clear • Occlusion: determines if there may be objects blocking the face in the image

Answer is correct. https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-face-detection

It should be face detection. https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-face-detection

The answer is Face Detection. Check face detection attributes here - https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-face-detection