Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F21%3APU143903" target="_blank" >RIV/00216305:26220/21:PU143903 - isvavai.cz</a>
Výsledek na webu
<a href="https://ieeexplore.ieee.org/document/9631567" target="_blank" >https://ieeexplore.ieee.org/document/9631567</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICUMT54235.2021.9631567" target="_blank" >10.1109/ICUMT54235.2021.9631567</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions
Popis výsledku v původním jazyce
Anomaly detection (AD) plays a key role in automated quality analysis in industrial production. Recent AD methods have shown great potential for the detection of visual defects in several real-world applications. Most of the datatsets used in AD research (e.g. MVTec AD) are composed mainly of images from the laboratory environment with a monochromatic background. Each image contains only one object, which is centred, and its distance and spatial orientation to the camera do not change significantly. However, these conditions cannot be achieved in many realworld manufacturing processes and production lines. In order to test the performance of state-of-the-art (SOTA) AD methods under conditions of variable spatial orientation, position and distance of multiple objects concerning the camera at different light intensities and with a non-homogeneous background, it is necessary to create a new dataset. In this paper, we introduce a new dataset focused specifically on the issue of defect detection during painted metal parts fabrication. Next, we evaluate the performance of current SOTA AD methods on the proposed dataset. Our results show that some SOTA AD methods, which perform well on the standard industrial anomaly detection datatset – MVTec AD, show significantly different performance on our dataset. AUROC image-level difference is up to 23.12%. If we average the scores for all methods on each dataset, we observe the difference of 15.24%. Our experiment shows that for further development and improvement of AD methods, it is necessary to test these methods on datasets based on specific real-world applications.
Název v anglickém jazyce
Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions
Popis výsledku anglicky
Anomaly detection (AD) plays a key role in automated quality analysis in industrial production. Recent AD methods have shown great potential for the detection of visual defects in several real-world applications. Most of the datatsets used in AD research (e.g. MVTec AD) are composed mainly of images from the laboratory environment with a monochromatic background. Each image contains only one object, which is centred, and its distance and spatial orientation to the camera do not change significantly. However, these conditions cannot be achieved in many realworld manufacturing processes and production lines. In order to test the performance of state-of-the-art (SOTA) AD methods under conditions of variable spatial orientation, position and distance of multiple objects concerning the camera at different light intensities and with a non-homogeneous background, it is necessary to create a new dataset. In this paper, we introduce a new dataset focused specifically on the issue of defect detection during painted metal parts fabrication. Next, we evaluate the performance of current SOTA AD methods on the proposed dataset. Our results show that some SOTA AD methods, which perform well on the standard industrial anomaly detection datatset – MVTec AD, show significantly different performance on our dataset. AUROC image-level difference is up to 23.12%. If we average the scores for all methods on each dataset, we observe the difference of 15.24%. Our experiment shows that for further development and improvement of AD methods, it is necessary to test these methods on datasets based on specific real-world applications.
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
20205 - Automation and control systems
Návaznosti výsledku
Projekt
<a href="/cs/project/FW03010273" target="_blank" >FW03010273: Defektoskopie lakovaných dílů s pomocí automatické adaptace neuronových sítí</a><br>
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Ostatní
Rok uplatnění
2021
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
2021 13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)
ISBN
978-1-6654-0219-4
ISSN
—
e-ISSN
—
Počet stran výsledku
6
Strana od-do
66-71
Název nakladatele
IEEE
Místo vydání
Online
Místo konání akce
Online
Datum konání akce
25. 10. 2021
Typ akce podle státní příslušnosti
CST - Celostátní akce
Kód UT WoS článku
—