Sensors (Basel). 2021 Jul 25;21(15). doi: 10.3390/s21155039.

Product Inspection Methodology via Deep Learning: An Overview.

Sensors (Basel, Switzerland)

Tae-Hyun Kim, Hye-Rin Kim, Yeong-Jun Cho

PMID: 34372276 PMCID: PMC8346960 DOI: 10.3390/s21155039

Abstract

In this study, we present a framework for product quality inspection based on deep learning techniques. First, we categorize several deep learning models that can be applied to product inspection systems. In addition, we explain the steps for building a deep-learning-based inspection system in detail. Second, we address connection schemes that efficiently link deep learning models to product inspection systems. Finally, we propose an effective method that can maintain and enhance a product inspection system according to improvement goals of the existing product inspection systems. The proposed system is observed to possess good system maintenance and stability owing to the proposed methods. All the proposed methods are integrated into a unified framework and we provide detailed explanations of each proposed method. In order to verify the effectiveness of the proposed system, we compare and analyze the performance of the methods in various test scenarios. We expect that our study will provide useful guidelines to readers who desire to implement deep-learning-based systems for product inspection.

Keywords: deep learning; defect inspection; machine vision; product inspection; smart factory; smart manufacturing

References

1. Trends Cogn Sci. 1999 Apr;3(4):128-135 - PubMed
2. Sensors (Basel). 2018 Aug 20;18(8): - PubMed

MeSH terms

• Consumer Product Safety*
• Deep Learning*

Publication Types

• Journal Article

Grant support

• 2017-0-00162/Korean government (MSIT)