Active learning and novel model calibration measurements for automated visual inspection in manufacturing

Rožanec, Jože Martin (author), Bizjak, Luka (author), Trajkova, Elena (author), Zajec, Patrik (author), Keizer, Jelle (author), Fortuna, Blaž (author), Mladenić, Dunja (author)

Quality control is a crucial activity performed by manufacturing enterprises to ensure that their products meet quality standards and avoid potential damage to the brand’s reputation. The decreased cost of sensors and connectivity enabled increasing digitalization of manufacturing. In addition, artificial intelligence enables higher degrees of automation, reducing overall costs and time required for defect inspection. This research compares three active learning approaches, having single and multiple oracles, to visual inspection. Six new metrics are proposed to assess the quality of calibration without the need for ground truth. Furthermore, this research explores whether existing calibrators can improve performance by leveraging an approximate ground truth to enlarge the calibration set. The experiments were performed on real-world data provided by Philips Consumer Lifestyle BV. Our results show that the explored active learning settings can reduce the data labeling effort by between three and four percent without detriment to the overall quality goals, considering a threshold of p = 0.95. Furthermore, the results show that the proposed calibration metrics successfully capture relevant information otherwise available to metrics used up to date only through ground truth data. Therefore, the proposed metrics can be used to estimate the quality of models’ probability calibration without committing to a labeling effort to obtain ground truth data.

• Language: English
• Keywords: active learning, smart manufacturing, probability calibration, artificial intelligence, machine learning, automated visual inspection
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FE - Faculty of Electrical Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2024
• Number of pages: Str. 1963–1984
• Numbering: Vol. 35, iss. 5
• PID: 20.500.12556/RUL-158239
• UDC: 658.5
• ISSN on article: 1572-8145
• DOI: 10.1007/s10845-023-02098-0
• COBISS.SI-ID: 181386243
• Publication date in RUL: 30.05.2024

Record is a part of a journal

• Title: Journal of intelligent manufacturing
• Shortened title: J. intell. manuf.
• Publisher: Springer Nature
• ISSN: 1572-8145
• COBISS.SI-ID: 513191705

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: pametna proizvodnja, nadzor proizvodnje, vizualni nadzor, zagotavljanje kakovosti, proizvodnja, aktivno učenje, umetna inteligenca, strojno učenje

Projects

• Funder: ARRS - Slovenian Research Agency

• Funder: EC - European Commission
• Funding programme: H2020
• Project number: 956573
• Name: Safe and Trusted Human Centric Artificial Intelligence in Future Manufacturing Lines
• Acronym: STAR