A beneficial dual transformation approach for deep learning networks used in steel surface defect detection

Fityanul Akhyar, Chih Yang Lin, Gugan S. Kathiresan

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

7 Scopus citations

Abstract

Steel surface defect detection represents a challenging task in real-world practical object detection. Based on our observations, there are two critical problems which create this challenge: the tiny size, and vagueness of the defects. To solve these problems, this study a proposes a deep learning-based defect detection system that uses automatic dual transformation in the end-to-end network. First, the original training images in RGB are transformed into the HSV color model to re-arrange the difference in color distribution. Second, the feature maps are upsampled using bilinear interpolation to maintain the smaller resolution. The latest and state-of-the-art object detection model, High-Resolution Network (HRNet) is utilized in this system, with initial transformation performed via data augmentation. Afterward, the output of the backbone stage is applied to the second transformation. According to the experimental results, the proposed approach increases the accuracy of the detection of class 1 Severstal steel surface defects by 3.6% versus the baseline.

Original languageEnglish
Title of host publicationICMR 2021 - Proceedings of the 2021 International Conference on Multimedia Retrieval
PublisherAssociation for Computing Machinery, Inc
Pages619-622
Number of pages4
ISBN (Electronic)9781450384636
DOIs
StatePublished - 24 Aug 2021
Event11th ACM International Conference on Multimedia Retrieval, ICMR 2021 - Taipei, Taiwan
Duration: 16 Nov 202119 Nov 2021

Publication series

NameICMR 2021 - Proceedings of the 2021 International Conference on Multimedia Retrieval

Conference

Conference11th ACM International Conference on Multimedia Retrieval, ICMR 2021
Country/TerritoryTaiwan
CityTaipei
Period16/11/2119/11/21

Keywords

  • Bilinear interpolation
  • Defect Detection system
  • High-resolution network
  • RGB to HSV

Fingerprint

Dive into the research topics of 'A beneficial dual transformation approach for deep learning networks used in steel surface defect detection'. Together they form a unique fingerprint.

Cite this