How to configure real-time image classification for quality control?

You work for a semiconductor manufacturing company. You need to create a real-time application that automates the quality control process. High-definition images of each semiconductor are taken at the end of the assembly line in real time. The photos are uploaded to a Cloud Storage bucket along with tabular data that includes each semiconductor’s batch number, serial number, dimensions, and weight. You need to configure model training and serving while maximizing model accuracy. What should you do?

Use Vertex AI Data Labeling Service to label the images, and tram an AutoML image classification model. Deploy the model, and configure Pub/Sub to publish a message when an image is categorized into the failing class. Source Reference Answer
Use Vertex AI Data Labeling Service to label the images, and train an AutoML image classification model. Schedule a daily batch prediction job that publishes a Pub/Sub message when the job completes.
Convert the images into an embedding representation. Import this data into BigQuery, and train a BigQuery ML K-means clustering model with two clusters. Deploy the model and configure Pub/Sub to publish a message when a semiconductor’s data is categorized into the failing cluster.
Import the tabular data into BigQuery, use Vertex AI Data Labeling Service to label the data and train an AutoML tabular classification model. Deploy the model, and configure Pub/Sub to publish a message when a semiconductor’s data is categorized into the failing class.

Community Votes

100%

100% of anonymous learners picked answer A. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

The question tests selecting the correct data source (images) and serving method (online prediction) to satisfy real-time constraints and maximize accuracy.

To achieve real-time quality control with high accuracy, use Vertex AI Data Labeling and AutoML Image Classification deployed for online prediction. This approach utilizes the visual data effectively and meets the low-latency requirement.

Choosing Option D is a common error because it focuses on the tabular data provided in the prompt but fails to utilize the high-definition images, which are the primary source for visual quality inspection.

Community Discussion (5 comments)

AzureDP900 👍 2

Option A is correct The high-definition images of each semiconductor are taken in real-time at the end of the assembly line. The images are uploaded to Cloud Storage along with tabular data that includes batch number, serial number, dimensions, and weight. You need to configure model training and serving while maximizing model accuracy.

omermahgoub 👍 4 Selected: A

Real-time Processing, uploading images to Cloud Storage triggers the AutoML image classification model for immediate processing, enabling real-time quality control decisions. Image Classification, the scenario focuses on classifying images as "passing" or "failing" quality, making image classification the appropriate approach. Pub/Sub Notifications, Pub/Sub messaging efficiently alerts downstream systems about failing classifications, allowing for prompt quality control actions.

b1a8fae 👍 3 Selected: A

I go with A.

pikachu007 👍 1 Selected: D

Option B: Batch prediction jobs introduce latency, making them unsuitable for real-time quality control. Option C: K-means clustering is an unsupervised learning technique that doesn't leverage labeled data to distinguish between passing and failing semiconductors, potentially compromising accuracy. Option D: Tabular classification focuses on structured data, not images, and might overlook visual defects captured in the photos.

daidai75 👍 2 Selected: A

The right answer should be A

Comments & Corrections

No comments yet — spotted an error or have a note? Share it below.

Expert Analysis

Why the Answer Is Correct

Option A is correct because it leverages the high-definition images, which are the primary data source for visual quality control. AutoML Image Classification is selected to maximize model accuracy, and deploying the model for online prediction ensures the real-time processing requirement is met. Pub/Sub is correctly used to trigger immediate alerts for failing items.

Why the Other Options Are Wrong

Option B is incorrect because a daily batch prediction job introduces significant latency, failing the real-time requirement. Option C is incorrect because K-means is an unsupervised clustering method that cannot reliably classify data into specific 'passing' or 'failing' categories without labels, compromising accuracy. Option D is incorrect because it ignores the image data entirely; relying solely on tabular data like weight and dimensions is insufficient for detecting visual defects on semiconductors.

Community Comment Notes

Community feedback confirms that Option A is the only solution satisfying the real-time constraint. Users noted that Option B is too slow, Option C uses the wrong algorithm (unsupervised), and Option D ignores the critical image data. The consensus aligns with using AutoML Vision for this use case.

Official Reference

Exam Strategy

When facing real-time requirements, immediately eliminate batch prediction options. Additionally, always prioritize the data modality (images vs. tabular) that directly addresses the core problem described in the scenario.

Related Analysis

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide