Show simple item record

dc.contributor.authorSaiz, Fátima A.en_US
dc.contributor.authorAlfaro, Garazien_US
dc.contributor.authorBarandiaran, Iñigoen_US
dc.contributor.authorGarcia, Saraen_US
dc.contributor.authorCarretero, M. P.en_US
dc.contributor.authorGraña, Manuelen_US
dc.contributor.editorOrtega, Lidia M. and Chica, Antonioen_US
dc.date.accessioned2021-09-21T08:08:56Z
dc.date.available2021-09-21T08:08:56Z
dc.date.issued2021
dc.identifier.isbn978-3-03868-160-1
dc.identifier.urihttps://doi.org/10.2312/ceig.20211355
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/ceig20211355
dc.description.abstractAutomated visual inspection is an ongoing machine vision challenge for industry. Faced with increasingly demanding quality standards it is reasonable to address the transition from a manual inspection system to an automatic one using some advanced machine learning approaches such as deep learning models. However, the introduction of neural models in environments such as the manufacturing industry find certain impairments or limitations. Indeed, due to the harsh conditions of manufacturing environments, there is usually the limitation of collecting a high quality database for training neural models. Also, the imbalance between non-defective and defective samples is very common issue in this type of scenarios. To alleviate these problems, this work proposes a pipeline to generate rendered images from CAD models of industrial components, to subsequently feed an anomaly detection model based on Deep Learning. Our approach can simulate the potential geometric and photometric transformations in which the parts could be presented to a real camera to faithfully reproduce the image acquisition behavior of an automatic inspection system. We evaluated the accuracy of several neural models trained with different synthetically generated data set simulating different transformations such as part temperature or part position and orientation with respect to a given camera. The results shows the feasibility of the proposed approach during the design and evaluation process of the image acquisition setup and to guarantee the success of the real future application.en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectQuality Inspection
dc.subjectIndustrial Manufacturing
dc.subjectPhoto realistic Rendering
dc.subjectCAD Models
dc.subjectAnomaly Detection
dc.subjectDeep Learning
dc.subjectGenerative Adversarial Networks
dc.titleSynthetic Data Set Generation for the Evaluation of Image Acquisition Strategies Applied to Deep Learning Based Industrial Component Inspection Systemsen_US
dc.description.seriesinformationSpanish Computer Graphics Conference (CEIG)
dc.description.sectionheadersFull Papers - Capture Techniques and Pathfinding
dc.identifier.doi10.2312/ceig.20211355
dc.identifier.pages1-8


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record