Visual inspection system for anomaly detection on KTL coatings using variational autoencoders

Kozamernik, Nejc (author), Bračun, Drago (author)

Electric cathode metal coating (KTL) is a popular choice for surface protection of metal components in the automotive industry. Due to the complex 3D shape of the parts and the glossy black color of the coating, machine vision inspection is very sensitive to variabilities among parts and to the variabilities in their positioning during the image acquisition. In this paper a variational autoencoder model for anomaly detection is presented to make further image processing more immune to variability and to detect coating defects more reliably.

• Language: English
• Keywords: surface defect inspection, imaging system, anomaly detection, deep generative models, variational autoencoders
• Work type: Article
• Typology: 1.08 - Published Scientific Conference Contribution
• Organization: FS - Faculty of Mechanical Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2020
• Number of pages: Str. 1558-1563
• Numbering: Vol. 93
• PID: 20.500.12556/RUL-121554
• UDC: 004.92:629.7(045)
• ISSN on article: 2212-8271
• DOI: 10.1016/j.procir.2020.04.114
• COBISS.SI-ID: 32754691
• Publication date in RUL: 15.10.2020

Record is a part of a proceedings

• Title: 53rd CIRP Conference on Manufacturing Systems 2020
• COBISS.SI-ID: 30177283

Record is a part of a journal

• Title: Procedia CIRP
• Publisher: Elsevier
• ISSN: 2212-8271
• COBISS.SI-ID: 12981019

Secondary language

• Language: Slovenian
• Keywords: KTL zaščita, iskanje površinskih napak, slikovni sistem, detekcija anomalij, globoki generativni model, variacijski avtoenkoder

Projects

• Funder: ARRS - Slovenian Research Agency
• Project number: P2-0270
• Name: Proizvodni sistemi, laserske tehnologije in spajanje materialov