2021/04/07 by Pierre Gutierrez, Maria Luschkova, Antoine Cordier +3 · 27 citations
Computer Science · Engineering · #Adaptation (eye) #Advanced Neural Network Applications #Advancements in Photolithography Techniques #Artificial intelligence #Complement (music) #Computer science #Computer vision #Deep learning #Domain (mathematical analysis) #Focus (optics) #Industrial Vision Systems and Defect Detection #Machine learning #Pattern recognition (psychology) #Pipeline (software) #Quality (philosophy) #Real-time computing #Training set #cs.AI #cs.CV #cs.LG
paper · pdf · doi:10.1117/12.2586824
published in arXiv (Cornell University), 13 (Cornell University) · 8 pages, 4 figures, to be published in QCAV 2021 conference, proceedings will by published by SPIE
arxiv created 2021/04/07 · openalex publication_date 2021/04/07 · arxiv updated 2021/07/23 · openalex created_date 2021/08/02 · openalex updated_date 2026/08/05
Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly: collecting, cleaning, and annotating the data is tedious and limits the speed at which a system can be deployed as everything the system must detect needs to be observed first. This can impede the inspection of rare defects, since very few samples can be collected by the manufacturer. In this work, we focus on simulations to solve this issue. We first present a generic simulation pipeline to render images of defective or healthy (non defective) parts. As metallic parts can be highly textured with small defects like holes, we design a texture scanning and generation method. We assess the quality of the generated images by training deep learning networks and by testing them on real data from a manufacturer. We demonstrate that we can achieve encouraging results on real defect detection using purely simulated data. Additionally, we are able to improve global performances by concatenating simulated and real data, showing that simulations can complement real images to boost performances. Lastly, using domain adaptation techniques helps improving slightly our final results.