The quiet revolution in machine vision - A state-of-the-art survey paper, including historical review, perspectives, and future directions

Smith, Melvyn L.; Smith, Lyndon N.; Hansen, Mark F.

Abstract

Over the past few years, what might not unreasonably be described as a true revolution has taken place in the field of machine vision, radically altering the way many things had previously been done and offering new and exciting opportunities for those able to quickly embrace and master the new techniques. Rapid developments in machine learning, largely enabled by faster GPU-equipped computing hardware, has facilitated an explosion of machine vision applications into hitherto extremely challenging or, in many cases, previously impossible to automate industrial tasks. Together with developments towards an internet of things and the availability of big data, these form key components of what many consider to be the fourth industrial revolution. This transformation has dramatically improved the efficacy of some existing machine vision activities, such as in manufacturing (e.g. inspection for quality control and quality assurance), security (e.g. facial biometrics) and in medicine (e.g. detecting cancers), while in other cases has opened up completely new areas of use, such as in agriculture and construction (as well as in the existing domains of manufacturing and medicine). Here we will explore the history and nature of this change, what underlies it, what enables it, and the impact it has had - the latter by reviewing several recent indicative applications described in the research literature. We will also consider the continuing role that traditional or classical machine vision might still play. Finally, the key future challenges and developing opportunities in machine vision will also be discussed.

• Journal Article Type: Article
• Acceptance Date: Apr 28, 2021
• Online Publication Date: May 15, 2021
• Publication Date: Sep 1, 2021
• Deposit Date: Apr 30, 2021
• Publicly Available Date: May 16, 2023
• Journal: Computers in Industry
• Print ISSN: 0166-3615
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 130
• Article Number: 103472
• DOI: https://doi.org/10.1016/j.compind.2021.103472
• Keywords: machine vision; machine learning; deep learning; state-of-the-art
• Public URL: https://uwe-repository.worktribe.com/output/7319734
• Publisher URL: Elsevier