Evaluation of Additional Augmented Images for Steel Surface Defect Detection

Isack Farady, Shashank, Megha Dey Sarkar, Wen Thong Chang, Chih Yang Lin

研究成果: 書貢獻/報告類型會議論文篇章同行評審

1 引文 斯高帕斯(Scopus)

摘要

Surface defects are one of the major causes of the unprecedented breakdown of machinery in industrial units. Due to several limiting factors, the real-time dataset can be less. This causes implications such as data imbalance and lack of defect samples thereby not yielding desired results. In this paper, we explored an augmentation way to enhance detection accuracy by adding new additional data based on pixel domain augmentation. Through this approach, we proved that the overall accuracy of the model is improved by about 4.38 % on the NEU Steel defect dataset compared to the baseline and conventional image augmentation.

原文???core.languages.en_GB???
主出版物標題Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面199-200
頁數2
ISBN(電子)9781665470506
DOIs
出版狀態已出版 - 2022
事件2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 - Taipei, Taiwan
持續時間: 6 7月 20228 7月 2022

出版系列

名字Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
國家/地區Taiwan
城市Taipei
期間6/07/228/07/22

指紋

深入研究「Evaluation of Additional Augmented Images for Steel Surface Defect Detection」主題。共同形成了獨特的指紋。

引用此