Evaluation of Additional Augmented Images for Steel Surface Defect Detection

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages199-200
Number of pages2
ISBN (Electronic)9781665470506
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 - Taipei, Taiwan
Duration: 6 Jul 20228 Jul 2022

Publication series

NameProceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

Conference

Conference2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
Country/TerritoryTaiwan
CityTaipei
Period6/07/228/07/22

Fingerprint

Dive into the research topics of 'Evaluation of Additional Augmented Images for Steel Surface Defect Detection'. Together they form a unique fingerprint.

Cite this