Convolutional neural network for industrial egg classification

Ryota Shimizu, Shusuke Yanagawa, Toru Shimizu, Mototsugu Hamada, Tadahiro Kuroda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

CNN (Convolutional Neural Network) is a powerful method for image classifying tasks. CNN's classifying capability is assessed by using large-scale image dataset such as ImageNet in many papers, but few works on CNN with small-scale dataset have been reported. We have been researching application method of Neural Network for classifying tasks in real-world for years [1]. In this work, we applied CNN to a quality inspection of industrial products and assessed its classifying capacity. Our CNN was trained with 2000 images of eggs taken in a factory, classified the images of almost 89,000 eggs into 6 qualities. Our method of combining multi-angle images into 1 image retained the 3-dimensional features of the object, and improved the classification accuracy to 92.3%. It confirmed that CNN is also effective for the quality inspection of industrial products.

Original languageEnglish
Title of host publicationProceedings - International SoC Design Conference 2017, ISOCC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages67-68
Number of pages2
ISBN (Electronic)9781538622858
DOIs
Publication statusPublished - 2018 May 29
Event14th International SoC Design Conference, ISOCC 2017 - Seoul, Korea, Republic of
Duration: 2017 Nov 52017 Nov 8

Other

Other14th International SoC Design Conference, ISOCC 2017
CountryKorea, Republic of
CitySeoul
Period17/11/517/11/8

Fingerprint

Neural networks
Inspection
Industrial plants

Keywords

  • Convolutional Neural Network
  • Image Classification
  • Quality Inspection
  • Small-scale Dataset

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Shimizu, R., Yanagawa, S., Shimizu, T., Hamada, M., & Kuroda, T. (2018). Convolutional neural network for industrial egg classification. In Proceedings - International SoC Design Conference 2017, ISOCC 2017 (pp. 67-68). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISOCC.2017.8368830

Convolutional neural network for industrial egg classification. / Shimizu, Ryota; Yanagawa, Shusuke; Shimizu, Toru; Hamada, Mototsugu; Kuroda, Tadahiro.

Proceedings - International SoC Design Conference 2017, ISOCC 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 67-68.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shimizu, R, Yanagawa, S, Shimizu, T, Hamada, M & Kuroda, T 2018, Convolutional neural network for industrial egg classification. in Proceedings - International SoC Design Conference 2017, ISOCC 2017. Institute of Electrical and Electronics Engineers Inc., pp. 67-68, 14th International SoC Design Conference, ISOCC 2017, Seoul, Korea, Republic of, 17/11/5. https://doi.org/10.1109/ISOCC.2017.8368830
Shimizu R, Yanagawa S, Shimizu T, Hamada M, Kuroda T. Convolutional neural network for industrial egg classification. In Proceedings - International SoC Design Conference 2017, ISOCC 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 67-68 https://doi.org/10.1109/ISOCC.2017.8368830
Shimizu, Ryota ; Yanagawa, Shusuke ; Shimizu, Toru ; Hamada, Mototsugu ; Kuroda, Tadahiro. / Convolutional neural network for industrial egg classification. Proceedings - International SoC Design Conference 2017, ISOCC 2017. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 67-68
@inproceedings{840a8b42b7fb45bc81971f5836686b00,
title = "Convolutional neural network for industrial egg classification",
abstract = "CNN (Convolutional Neural Network) is a powerful method for image classifying tasks. CNN's classifying capability is assessed by using large-scale image dataset such as ImageNet in many papers, but few works on CNN with small-scale dataset have been reported. We have been researching application method of Neural Network for classifying tasks in real-world for years [1]. In this work, we applied CNN to a quality inspection of industrial products and assessed its classifying capacity. Our CNN was trained with 2000 images of eggs taken in a factory, classified the images of almost 89,000 eggs into 6 qualities. Our method of combining multi-angle images into 1 image retained the 3-dimensional features of the object, and improved the classification accuracy to 92.3{\%}. It confirmed that CNN is also effective for the quality inspection of industrial products.",
keywords = "Convolutional Neural Network, Image Classification, Quality Inspection, Small-scale Dataset",
author = "Ryota Shimizu and Shusuke Yanagawa and Toru Shimizu and Mototsugu Hamada and Tadahiro Kuroda",
year = "2018",
month = "5",
day = "29",
doi = "10.1109/ISOCC.2017.8368830",
language = "English",
pages = "67--68",
booktitle = "Proceedings - International SoC Design Conference 2017, ISOCC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Convolutional neural network for industrial egg classification

AU - Shimizu, Ryota

AU - Yanagawa, Shusuke

AU - Shimizu, Toru

AU - Hamada, Mototsugu

AU - Kuroda, Tadahiro

PY - 2018/5/29

Y1 - 2018/5/29

N2 - CNN (Convolutional Neural Network) is a powerful method for image classifying tasks. CNN's classifying capability is assessed by using large-scale image dataset such as ImageNet in many papers, but few works on CNN with small-scale dataset have been reported. We have been researching application method of Neural Network for classifying tasks in real-world for years [1]. In this work, we applied CNN to a quality inspection of industrial products and assessed its classifying capacity. Our CNN was trained with 2000 images of eggs taken in a factory, classified the images of almost 89,000 eggs into 6 qualities. Our method of combining multi-angle images into 1 image retained the 3-dimensional features of the object, and improved the classification accuracy to 92.3%. It confirmed that CNN is also effective for the quality inspection of industrial products.

AB - CNN (Convolutional Neural Network) is a powerful method for image classifying tasks. CNN's classifying capability is assessed by using large-scale image dataset such as ImageNet in many papers, but few works on CNN with small-scale dataset have been reported. We have been researching application method of Neural Network for classifying tasks in real-world for years [1]. In this work, we applied CNN to a quality inspection of industrial products and assessed its classifying capacity. Our CNN was trained with 2000 images of eggs taken in a factory, classified the images of almost 89,000 eggs into 6 qualities. Our method of combining multi-angle images into 1 image retained the 3-dimensional features of the object, and improved the classification accuracy to 92.3%. It confirmed that CNN is also effective for the quality inspection of industrial products.

KW - Convolutional Neural Network

KW - Image Classification

KW - Quality Inspection

KW - Small-scale Dataset

UR - http://www.scopus.com/inward/record.url?scp=85048859630&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048859630&partnerID=8YFLogxK

U2 - 10.1109/ISOCC.2017.8368830

DO - 10.1109/ISOCC.2017.8368830

M3 - Conference contribution

AN - SCOPUS:85048859630

SP - 67

EP - 68

BT - Proceedings - International SoC Design Conference 2017, ISOCC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -