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

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

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.

• Jezik: Angleški jezik
• Ključne besede: active learning, smart manufacturing, probability calibration, artificial intelligence, machine learning, automated visual inspection
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FE - Fakulteta za elektrotehniko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2024
• Št. strani: Str. 1963–1984
• Številčenje: Vol. 35, iss. 5
• PID: 20.500.12556/RUL-158239
• UDK: 658.5
• ISSN pri članku: 1572-8145
• DOI: 10.1007/s10845-023-02098-0
• COBISS.SI-ID: 181386243
• Datum objave v RUL: 30.05.2024

ROŽANEC, Jože Martin, BIZJAK, Luka, TRAJKOVA, Elena, ZAJEC, Patrik, KEIZER, Jelle, FORTUNA, Blaž in MLADENIĆ, Dunja, 2024, Active learning and novel model calibration measurements for automated visual inspection in manufacturing. Journal of intelligent manufacturing [na spletu]. 2024. Vol. 35, no. 5. [Dostopano 3 maj 2025]. DOI 10.1007/s10845-023-02098-0. Pridobljeno s: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=slv&id=158239

Gradivo je del revije

• Naslov: Journal of intelligent manufacturing
• Skrajšan naslov: J. intell. manuf.
• Založnik: Springer Nature
• ISSN: 1572-8145
• COBISS.SI-ID: 513191705

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: pametna proizvodnja, nadzor proizvodnje, vizualni nadzor, zagotavljanje kakovosti, proizvodnja, aktivno učenje, umetna inteligenca, strojno učenje

Projekti

• Financer: ARRS - Agencija za raziskovalno dejavnost Republike Slovenije

• Financer: EC - European Commission
• Program financ.: H2020
• Številka projekta: 956573
• Naslov: Safe and Trusted Human Centric Artificial Intelligence in Future Manufacturing Lines
• Akronim: STAR