GAN-based Defect Image Generation for Imbalanced Defect Classification of OLED panels

Simple item page
dc.contributor.authorJeon, Yongmoonen_US
dc.contributor.authorKim, Haneolen_US
dc.contributor.authorLee, Hyeonaen_US
dc.contributor.authorJo, Seonghoonen_US
dc.contributor.authorKim, Jaewonen_US
dc.contributor.editorGhosh, Abhijeeten_US
dc.contributor.editorWei, Li-Yien_US
dc.date.accessioned2022-07-01T15:38:37Z
dc.date.available2022-07-01T15:38:37Z
dc.date.issued2022
dc.description.abstractImage classification based on neural networks has been widely explored in machine learning and most research have focused on developing more efficient and accurate network models for given image dataset mostly over natural scene. However, industrial image data have different features with natural scene images in shape of target objects, background patterns, and color. Additionally, data imbalance is one of the most challenging problems to degrade classification accuracy for industrial images. This paper proposes a novel GAN-based image generation method to improve classification accuracy for defect images of OLED panels. We validate our method can synthetically generate defect images of OLED panels and classification accuracy can be improved by training minor classes with the generated defect images.en_US
dc.description.sectionheadersIndustry Track Papers
dc.description.seriesinformationEurographics Symposium on Rendering
dc.identifier.doi10.2312/sr.20221164
dc.identifier.isbn978-3-03868-187-8
dc.identifier.issn1727-3463
dc.identifier.pages145-150
dc.identifier.pages6 pages
dc.identifier.urihttps://doi.org/10.2312/sr.20221164
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/sr20221164
dc.publisherThe Eurographics Associationen_US
dc.subjectCCS Concepts: Applied computing --> Computer-aided design
dc.subjectApplied computing
dc.subjectComputer
dc.subjectaided design
dc.titleGAN-based Defect Image Generation for Imbalanced Defect Classification of OLED panelsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
145-150.pdf
Size:
5.27 MB
Format:
Adobe Portable Document Format
Download
Collections
Rendering 2022 - Symposium Track