Detection of fractures in glass using photographs

• Main Author: Tchen, Jee Wern
• Other Authors: Zheng Jianmin
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/165652
• Institution: Nanyang Technological University

Within machine vision, an actively researched topic is automatic inspection and defect detection using visual data such as images and videos. The technique is widely adopted due to its ability to overcome the limitations of traditional inspection approaches, in the quality inspection of metal parts in machinery. Traditionally, the process is heavily dependent on human labor, Therefore, the swap to automatic inspection can contribute to improved efficiency and performance. However, to the author's knowledge, there is little extant research on the automatic inspection of materials and products used by end-consumers. The majority of automatic inspection and defect detection processes used in industrial production give rise to high accuracy but are correspondingly highly costly to carry out. The majority of end-consumers are unlikely to be able to readily purchase such equipment, i.e. lighting machinery. Hence, this project successfully produced a novel pipeline that can assist end-consumers in glass defect detection in an accessible and affordable manner. This work is part of the research project "Artificial Intelligence for Smart Image Understanding" at Rolls-Royce@NTU Corporate Lab