Publication Date
2025
Document Type
Dissertation/Thesis
First Advisor
Chen, Niechen
Degree Name
M.S. (Master of Science)
Legacy Department
Department of Industrial and Systems Engineering
Abstract
Modern computer vision (CV) systems largely depend on real-world data for training, which is costly in terms of time, materials, and resources. As industries push toward automation and Artificial Intelligence (AI) -driven solutions, the need for enabling more efficient model training is growing. The primary aim of this work is to explore a framework tailored for industrial applications that uses synthetic images generated from 3D models to train a CV model capable of real-world object detection. This approach seeks to reduce the time, cost, and resources typically required for training AI models with real-world data. This work presents a method for efficient AI-CV model training with synthetic image data, in which an image rendering software is used to create 3D environments populated with CAD models of interest, then generate synthetic images with color and depth information. These images will then be used to train a state-of-the-art CV Neural Network (NN) architectures to recognize objects and extract critical object information for manufacturing purposes, including object segmentation, key point localization, and orientation identification. Through the proposed method in this work, it is expected that a robust AI-CV model can be efficiently and effectively trained to detect and identify real-world objects using synthetic image training data derived from 3D models. This work aims to explore the effectiveness of using synthetic data to replace real-world data in certain applications. This approach has potential to broaden the application and lower the hurdle of implementing CV systems, particularly in automation and quality inspection processes.
Recommended Citation
Moraga, Reinaldo A., "Leveraging Synthetic Data for Efficient Training of AI Models for Real-World Object Detection" (2025). Graduate Research Theses & Dissertations. 8078.
https://huskiecommons.lib.niu.edu/allgraduate-thesesdissertations/8078
Extent
46 pages
Language
en
Publisher
Northern Illinois University
Rights Statement
In Copyright
Rights Statement 2
NIU theses are protected by copyright. They may be viewed from Huskie Commons for any purpose, but reproduction or distribution in any format is prohibited without the written permission of the authors.
Media Type
Text
