Course Filter

Course type
Duration
Hours
Target
Topics
Language
Proficiency
Certificate selection
Instructor organization
Price
Eur

Preprocessing for Convolutional Neural Network

By University of Groningen

Type of course:

Digital learning, Lesson

Language:

EN

Duration:

15 minutes

Proficiency:

Intermediate

Target:

Manager, Professionals, Workers

Effective preprocessing is key to turning raw visual data into a resource that AI models can use to accurately detect anomalies in manufacturing. But how can you enhance the visibility of defects while preserving important details about your products?

In this lesson, we’ll explore the core preprocessing methods used to prepare visual data in manufacturing environments. You’ll learn how to resize images for consistency, reduce noise to improve clarity, and enhance contrast to make defects more visible while still maintaining critical product details. We’ll also cover normalization and standardization techniques to ensure consistency across batches, improving the reliability and performance of Convolutional Neural Networks (CNNs) used in quality control.

By the end of this lesson, you’ll be able to apply preprocessing techniques to refine image data, enhance defect detection, and prepare your dataset for use in CNN models, ensuring more accurate, resilient, and effective quality control in real-world manufacturing applications.

About The Author

Dilek Dustegor is a Professor of Computing Science at the University of Groningen in the Netherlands. She is interested in bridging the gaps between research, development and implementation using AI and automation. She is pursuing research about modeling, design and analysis of large scale / networked systems using Internet of Things (IoT) and Machine Learning (ML) techniques, with a special interest in smart city applications. She is a seasoned educator, and loves using the newest educational technologies for an enhanced learning experience.


Learning outcomes

  1. By the end of this lesson, learners will be able to identify and apply core preprocessing methods, including resizing, noise reduction, and contrast enhancement, to prepare visual data from sensors and cameras in manufacturing environments.
  2. By the end of this lesson, learners will be able to refine image data, balancing the enhancement of defect visibility with the preservation of critical details.
  3. By the end of this lesson, learners will be able to apply normalization and standardization to your dataset to achieve consistency across batches, making your convolutional neural network (CNN) models more resilient and reliable in real-world quality control applications.

Topics

Automation and Sensoring, Automation and Robotics, Digital Transformation, Machine Learning

Provided by

Content created in 2024
Take the next step toward your learning goals

Course Includes

  • 1 Quiz

Related