Design Tool of Deep Convolutional Neural Network for Intelligent Visual Inspection

Fusaomi Nagata, Kenta Tokuno, Akimasa Otsuka, Takeshi Ikeda, Hiroaki Ochi, Keigo Watanabe, Maki K. Habib

Research output: Contribution to journalConference article

Abstract

Recently, convolutional neural networks (CNNs) are used essentially to classify images as it helps to cluster them by similarity and perform recognition. In this paper, a design tool that helps to develop different deep CNNs (DCNNs) is presented. As an example, a DCNN is designed by using the developed tool to use it for vision based inspection to recognize undesirable defects such as crack, burr, protrusion and chipping which normally occur in the manufacturing process of resin molded articles. An image generator is implemented to efficiently produce many similar images for training. Similar images are easily generated by rotating, translating, scaling and transforming original images. The designed DCNN is trained by using the produced images and then tested through classification experiments. The usefulness of the design tool and the basic performance of the designed DCNN are introduced.

Original languageEnglish
Article number012073
JournalIOP Conference Series: Materials Science and Engineering
Volume423
Issue number1
DOIs
Publication statusPublished - Nov 6 2018
Event2018 4th International Conference on Applied Materials and Manufacturing Technology, ICAMMT 2018 - Nanchang, China
Duration: May 25 2018May 27 2018

Fingerprint

Inspection
Neural networks
Resins
Cracks
Defects
Experiments

ASJC Scopus subject areas

  • Materials Science(all)
  • Engineering(all)

Cite this

Design Tool of Deep Convolutional Neural Network for Intelligent Visual Inspection. / Nagata, Fusaomi; Tokuno, Kenta; Otsuka, Akimasa; Ikeda, Takeshi; Ochi, Hiroaki; Watanabe, Keigo; Habib, Maki K.

In: IOP Conference Series: Materials Science and Engineering, Vol. 423, No. 1, 012073, 06.11.2018.

Research output: Contribution to journalConference article

Nagata, Fusaomi ; Tokuno, Kenta ; Otsuka, Akimasa ; Ikeda, Takeshi ; Ochi, Hiroaki ; Watanabe, Keigo ; Habib, Maki K. / Design Tool of Deep Convolutional Neural Network for Intelligent Visual Inspection. In: IOP Conference Series: Materials Science and Engineering. 2018 ; Vol. 423, No. 1.
@article{7a0fb367c417451ab12938eb88006041,
title = "Design Tool of Deep Convolutional Neural Network for Intelligent Visual Inspection",
abstract = "Recently, convolutional neural networks (CNNs) are used essentially to classify images as it helps to cluster them by similarity and perform recognition. In this paper, a design tool that helps to develop different deep CNNs (DCNNs) is presented. As an example, a DCNN is designed by using the developed tool to use it for vision based inspection to recognize undesirable defects such as crack, burr, protrusion and chipping which normally occur in the manufacturing process of resin molded articles. An image generator is implemented to efficiently produce many similar images for training. Similar images are easily generated by rotating, translating, scaling and transforming original images. The designed DCNN is trained by using the produced images and then tested through classification experiments. The usefulness of the design tool and the basic performance of the designed DCNN are introduced.",
author = "Fusaomi Nagata and Kenta Tokuno and Akimasa Otsuka and Takeshi Ikeda and Hiroaki Ochi and Keigo Watanabe and Habib, {Maki K.}",
year = "2018",
month = "11",
day = "6",
doi = "10.1088/1757-899X/423/1/012073",
language = "English",
volume = "423",
journal = "IOP Conference Series: Materials Science and Engineering",
issn = "1757-8981",
publisher = "IOP Publishing Ltd.",
number = "1",

}

TY - JOUR

T1 - Design Tool of Deep Convolutional Neural Network for Intelligent Visual Inspection

AU - Nagata, Fusaomi

AU - Tokuno, Kenta

AU - Otsuka, Akimasa

AU - Ikeda, Takeshi

AU - Ochi, Hiroaki

AU - Watanabe, Keigo

AU - Habib, Maki K.

PY - 2018/11/6

Y1 - 2018/11/6

N2 - Recently, convolutional neural networks (CNNs) are used essentially to classify images as it helps to cluster them by similarity and perform recognition. In this paper, a design tool that helps to develop different deep CNNs (DCNNs) is presented. As an example, a DCNN is designed by using the developed tool to use it for vision based inspection to recognize undesirable defects such as crack, burr, protrusion and chipping which normally occur in the manufacturing process of resin molded articles. An image generator is implemented to efficiently produce many similar images for training. Similar images are easily generated by rotating, translating, scaling and transforming original images. The designed DCNN is trained by using the produced images and then tested through classification experiments. The usefulness of the design tool and the basic performance of the designed DCNN are introduced.

AB - Recently, convolutional neural networks (CNNs) are used essentially to classify images as it helps to cluster them by similarity and perform recognition. In this paper, a design tool that helps to develop different deep CNNs (DCNNs) is presented. As an example, a DCNN is designed by using the developed tool to use it for vision based inspection to recognize undesirable defects such as crack, burr, protrusion and chipping which normally occur in the manufacturing process of resin molded articles. An image generator is implemented to efficiently produce many similar images for training. Similar images are easily generated by rotating, translating, scaling and transforming original images. The designed DCNN is trained by using the produced images and then tested through classification experiments. The usefulness of the design tool and the basic performance of the designed DCNN are introduced.

UR - http://www.scopus.com/inward/record.url?scp=85057374890&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057374890&partnerID=8YFLogxK

U2 - 10.1088/1757-899X/423/1/012073

DO - 10.1088/1757-899X/423/1/012073

M3 - Conference article

AN - SCOPUS:85057374890

VL - 423

JO - IOP Conference Series: Materials Science and Engineering

JF - IOP Conference Series: Materials Science and Engineering

SN - 1757-8981

IS - 1

M1 - 012073

ER -