汽车油漆缺陷分类:使用CG软件进行深度学习模型的工厂特定数据生成

IF 0.6 4区 计算机科学 Q4 IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY
Kazuki Iwata, Haotong Guo, Ryuichi Yoshida, Yoshihito Souma, Chawan Koopipat, Masato Takahashi, Norimichi Tsumura
{"title":"汽车油漆缺陷分类:使用CG软件进行深度学习模型的工厂特定数据生成","authors":"Kazuki Iwata, Haotong Guo, Ryuichi Yoshida, Yoshihito Souma, Chawan Koopipat, Masato Takahashi, Norimichi Tsumura","doi":"10.2352/j.imagingsci.technol.2023.67.5.050412","DOIUrl":null,"url":null,"abstract":"In recent years, the advances in technology for detecting paint defects on exterior surfaces of automobiles have led to the emergence of research on automatic classification of defect types using deep learning. To develop a deep-learning model capable of identifying defect types, a large dataset consisting of sequential images of paint defects captured during inspection is required. However, generating such a dataset for each factory using actual measurements is expensive. Therefore, we propose a method for generating datasets to train deep-learning models in each factory by simulating images using computer graphics.","PeriodicalId":15924,"journal":{"name":"Journal of Imaging Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.6000,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Automotive Paint Defect Classification: Factory-Specific Data Generation using CG Software for Deep-Learning Models\",\"authors\":\"Kazuki Iwata, Haotong Guo, Ryuichi Yoshida, Yoshihito Souma, Chawan Koopipat, Masato Takahashi, Norimichi Tsumura\",\"doi\":\"10.2352/j.imagingsci.technol.2023.67.5.050412\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent years, the advances in technology for detecting paint defects on exterior surfaces of automobiles have led to the emergence of research on automatic classification of defect types using deep learning. To develop a deep-learning model capable of identifying defect types, a large dataset consisting of sequential images of paint defects captured during inspection is required. However, generating such a dataset for each factory using actual measurements is expensive. Therefore, we propose a method for generating datasets to train deep-learning models in each factory by simulating images using computer graphics.\",\"PeriodicalId\":15924,\"journal\":{\"name\":\"Journal of Imaging Science and Technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.6000,\"publicationDate\":\"2023-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Imaging Science and Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2352/j.imagingsci.technol.2023.67.5.050412\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Imaging Science and Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2352/j.imagingsci.technol.2023.67.5.050412","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

近年来,随着汽车外表面油漆缺陷检测技术的进步,利用深度学习对缺陷类型进行自动分类的研究应运而生。为了开发能够识别缺陷类型的深度学习模型,需要一个由检查期间捕获的油漆缺陷序列图像组成的大型数据集。然而,使用实际测量值为每个工厂生成这样的数据集是昂贵的。因此,我们提出了一种生成数据集的方法,通过使用计算机图形学模拟图像来训练每个工厂的深度学习模型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Automotive Paint Defect Classification: Factory-Specific Data Generation using CG Software for Deep-Learning Models
In recent years, the advances in technology for detecting paint defects on exterior surfaces of automobiles have led to the emergence of research on automatic classification of defect types using deep learning. To develop a deep-learning model capable of identifying defect types, a large dataset consisting of sequential images of paint defects captured during inspection is required. However, generating such a dataset for each factory using actual measurements is expensive. Therefore, we propose a method for generating datasets to train deep-learning models in each factory by simulating images using computer graphics.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Imaging Science and Technology
Journal of Imaging Science and Technology 工程技术-成像科学与照相技术
CiteScore
2.00
自引率
10.00%
发文量
45
审稿时长
>12 weeks
期刊介绍: Typical issues include research papers and/or comprehensive reviews from a variety of topical areas. In the spirit of fostering constructive scientific dialog, the Journal accepts Letters to the Editor commenting on previously published articles. Periodically the Journal features a Special Section containing a group of related— usually invited—papers introduced by a Guest Editor. Imaging research topics that have coverage in JIST include: Digital fabrication and biofabrication; Digital printing technologies; 3D imaging: capture, display, and print; Augmented and virtual reality systems; Mobile imaging; Computational and digital photography; Machine vision and learning; Data visualization and analysis; Image and video quality evaluation; Color image science; Image archiving, permanence, and security; Imaging applications including astronomy, medicine, sports, and autonomous vehicles.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信