TaylorMade Visual Burr Detection for High-mix Low-volume Production of Non-convex Cylindrical Metal Objects

Tashiro Kyosuke, Takeda Koji, Aoki Shogo, Ye Haoming, Hiroki Tomoe, Tanaka Kanji

2022

Abstract

Visual defect detection (VDD) for high-mix low-volume production of non-convex metal objects, such as high-pressure cylindrical piping joint parts (VDD-HPPPs), is challenging because subtle difference in domain (e.g., metal objects, imaging device, viewpoints, lighting) significantly affects the specular reflection characteristics of individual metal object types. In this paper, we address this issue by introducing a tailor-made VDD framework that can be automatically adapted to a new domain. Specifically, we formulate this adaptation task as the problem of network architecture search (NAS) on a deep object-detection network, in which the network architecture is searched via reinforcement learning. We demonstrate the effectiveness of the proposed framework using the VDD-HPPPs task as a factory case study. Experimental results show that the proposed method achieved higher burr detection accuracy compared with the baseline method for data with different training/test domains for the non-convex HPPPs, which are particularly affected by domain shifts.

Paper Citation

in Harvard Style

Kyosuke T., Koji T., Shogo A., Haoming Y., Tomoe H. and Kanji T. (2022). TaylorMade Visual Burr Detection for High-mix Low-volume Production of Non-convex Cylindrical Metal Objects. In Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-549-4, pages 395-400. DOI: 10.5220/0010816000003122

in Bibtex Style

@conference{icpram22,
author={Tashiro Kyosuke and Takeda Koji and Aoki Shogo and Ye Haoming and Hiroki Tomoe and Tanaka Kanji},
title={TaylorMade Visual Burr Detection for High-mix Low-volume Production of Non-convex Cylindrical Metal Objects},
booktitle={Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2022},
pages={395-400},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010816000003122},
isbn={978-989-758-549-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - TaylorMade Visual Burr Detection for High-mix Low-volume Production of Non-convex Cylindrical Metal Objects
SN - 978-989-758-549-4
AU - Kyosuke T.
AU - Koji T.
AU - Shogo A.
AU - Haoming Y.
AU - Tomoe H.
AU - Kanji T.
PY - 2022
SP - 395
EP - 400
DO - 10.5220/0010816000003122