A Labor-Efficient GAN-based Model Generation Scheme for Deep-Learning Defect Inspection among Dense Beans in Coffee Industry

Cheng Ju Kuo, Chao Chun Chen, Tzu Ting Chen, Zhijing Tsai, Min Hsiung Hung, Yu Chuan Lin, Yi Chung Chen, Ding Chau Wang, Gwo Jiun Homg, Wei Tsung Su

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

Abstract

Coffee beans are one of most valuable agricultural products in the world, and defective bean removal plays a critical role to produce high-quality coffee products. In this work, we propose a novel labor-efficient deep learning-based model generation scheme, aiming at providing an effective model with less human labeling effort. The key idea is to iteratively generate new training images containing defective beans in various locations by using a generative-adversarial network framework, and these images incur low successful detection rate so that they are useful for improving model quality. Our proposed scheme brings two main impacts to the intelligent agriculture. First, our proposed scheme is the first work to reduce human labeling effort among solutions of vision-based defective bean removal. Second, our scheme can inspect all classes of defective beans categorized by the SCAA (Specialty Coffee Association of America) at the same time. The above two advantages increase the degree of automation to the coffee industry. We implement the prototype of the proposed scheme for conducting integrated tests. Testin. results of a case study reveal that the proposed scheme ca] efficiently and effectively generating models for identifyin defect beans.Our implementation of the proposed scheme is available a https://github.com/Louis8582/LEGAN.

Original languageEnglish
Title of host publication2019 IEEE 15th International Conference on Automation Science and Engineering, CASE 2019
PublisherIEEE Computer Society
Pages263-270
Number of pages8
ISBN (Electronic)9781728103556
DOIs
Publication statusPublished - 2019 Aug
Event15th IEEE International Conference on Automation Science and Engineering, CASE 2019 - Vancouver, Canada
Duration: 2019 Aug 222019 Aug 26

Publication series

NameIEEE International Conference on Automation Science and Engineering
Volume2019-August
ISSN (Print)2161-8070
ISSN (Electronic)2161-8089

Conference

Conference15th IEEE International Conference on Automation Science and Engineering, CASE 2019
CountryCanada
CityVancouver
Period19-08-2219-08-26

Fingerprint

Coffee
Inspection
Personnel
Defects
Labeling
Industry
Agricultural products
Agriculture
Automation
Deep learning

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Kuo, C. J., Chen, C. C., Chen, T. T., Tsai, Z., Hung, M. H., Lin, Y. C., ... Su, W. T. (2019). A Labor-Efficient GAN-based Model Generation Scheme for Deep-Learning Defect Inspection among Dense Beans in Coffee Industry. In 2019 IEEE 15th International Conference on Automation Science and Engineering, CASE 2019 (pp. 263-270). [8843259] (IEEE International Conference on Automation Science and Engineering; Vol. 2019-August). IEEE Computer Society. https://doi.org/10.1109/COASE.2019.8843259
Kuo, Cheng Ju ; Chen, Chao Chun ; Chen, Tzu Ting ; Tsai, Zhijing ; Hung, Min Hsiung ; Lin, Yu Chuan ; Chen, Yi Chung ; Wang, Ding Chau ; Homg, Gwo Jiun ; Su, Wei Tsung. / A Labor-Efficient GAN-based Model Generation Scheme for Deep-Learning Defect Inspection among Dense Beans in Coffee Industry. 2019 IEEE 15th International Conference on Automation Science and Engineering, CASE 2019. IEEE Computer Society, 2019. pp. 263-270 (IEEE International Conference on Automation Science and Engineering).
@inproceedings{5d87bb17b7d8465b8f10f6e1bf71ed28,
title = "A Labor-Efficient GAN-based Model Generation Scheme for Deep-Learning Defect Inspection among Dense Beans in Coffee Industry",
abstract = "Coffee beans are one of most valuable agricultural products in the world, and defective bean removal plays a critical role to produce high-quality coffee products. In this work, we propose a novel labor-efficient deep learning-based model generation scheme, aiming at providing an effective model with less human labeling effort. The key idea is to iteratively generate new training images containing defective beans in various locations by using a generative-adversarial network framework, and these images incur low successful detection rate so that they are useful for improving model quality. Our proposed scheme brings two main impacts to the intelligent agriculture. First, our proposed scheme is the first work to reduce human labeling effort among solutions of vision-based defective bean removal. Second, our scheme can inspect all classes of defective beans categorized by the SCAA (Specialty Coffee Association of America) at the same time. The above two advantages increase the degree of automation to the coffee industry. We implement the prototype of the proposed scheme for conducting integrated tests. Testin. results of a case study reveal that the proposed scheme ca] efficiently and effectively generating models for identifyin defect beans.Our implementation of the proposed scheme is available a https://github.com/Louis8582/LEGAN.",
author = "Kuo, {Cheng Ju} and Chen, {Chao Chun} and Chen, {Tzu Ting} and Zhijing Tsai and Hung, {Min Hsiung} and Lin, {Yu Chuan} and Chen, {Yi Chung} and Wang, {Ding Chau} and Homg, {Gwo Jiun} and Su, {Wei Tsung}",
year = "2019",
month = "8",
doi = "10.1109/COASE.2019.8843259",
language = "English",
series = "IEEE International Conference on Automation Science and Engineering",
publisher = "IEEE Computer Society",
pages = "263--270",
booktitle = "2019 IEEE 15th International Conference on Automation Science and Engineering, CASE 2019",
address = "United States",

}

Kuo, CJ, Chen, CC, Chen, TT, Tsai, Z, Hung, MH, Lin, YC, Chen, YC, Wang, DC, Homg, GJ & Su, WT 2019, A Labor-Efficient GAN-based Model Generation Scheme for Deep-Learning Defect Inspection among Dense Beans in Coffee Industry. in 2019 IEEE 15th International Conference on Automation Science and Engineering, CASE 2019., 8843259, IEEE International Conference on Automation Science and Engineering, vol. 2019-August, IEEE Computer Society, pp. 263-270, 15th IEEE International Conference on Automation Science and Engineering, CASE 2019, Vancouver, Canada, 19-08-22. https://doi.org/10.1109/COASE.2019.8843259

A Labor-Efficient GAN-based Model Generation Scheme for Deep-Learning Defect Inspection among Dense Beans in Coffee Industry. / Kuo, Cheng Ju; Chen, Chao Chun; Chen, Tzu Ting; Tsai, Zhijing; Hung, Min Hsiung; Lin, Yu Chuan; Chen, Yi Chung; Wang, Ding Chau; Homg, Gwo Jiun; Su, Wei Tsung.

2019 IEEE 15th International Conference on Automation Science and Engineering, CASE 2019. IEEE Computer Society, 2019. p. 263-270 8843259 (IEEE International Conference on Automation Science and Engineering; Vol. 2019-August).

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

TY - GEN

T1 - A Labor-Efficient GAN-based Model Generation Scheme for Deep-Learning Defect Inspection among Dense Beans in Coffee Industry

AU - Kuo, Cheng Ju

AU - Chen, Chao Chun

AU - Chen, Tzu Ting

AU - Tsai, Zhijing

AU - Hung, Min Hsiung

AU - Lin, Yu Chuan

AU - Chen, Yi Chung

AU - Wang, Ding Chau

AU - Homg, Gwo Jiun

AU - Su, Wei Tsung

PY - 2019/8

Y1 - 2019/8

N2 - Coffee beans are one of most valuable agricultural products in the world, and defective bean removal plays a critical role to produce high-quality coffee products. In this work, we propose a novel labor-efficient deep learning-based model generation scheme, aiming at providing an effective model with less human labeling effort. The key idea is to iteratively generate new training images containing defective beans in various locations by using a generative-adversarial network framework, and these images incur low successful detection rate so that they are useful for improving model quality. Our proposed scheme brings two main impacts to the intelligent agriculture. First, our proposed scheme is the first work to reduce human labeling effort among solutions of vision-based defective bean removal. Second, our scheme can inspect all classes of defective beans categorized by the SCAA (Specialty Coffee Association of America) at the same time. The above two advantages increase the degree of automation to the coffee industry. We implement the prototype of the proposed scheme for conducting integrated tests. Testin. results of a case study reveal that the proposed scheme ca] efficiently and effectively generating models for identifyin defect beans.Our implementation of the proposed scheme is available a https://github.com/Louis8582/LEGAN.

AB - Coffee beans are one of most valuable agricultural products in the world, and defective bean removal plays a critical role to produce high-quality coffee products. In this work, we propose a novel labor-efficient deep learning-based model generation scheme, aiming at providing an effective model with less human labeling effort. The key idea is to iteratively generate new training images containing defective beans in various locations by using a generative-adversarial network framework, and these images incur low successful detection rate so that they are useful for improving model quality. Our proposed scheme brings two main impacts to the intelligent agriculture. First, our proposed scheme is the first work to reduce human labeling effort among solutions of vision-based defective bean removal. Second, our scheme can inspect all classes of defective beans categorized by the SCAA (Specialty Coffee Association of America) at the same time. The above two advantages increase the degree of automation to the coffee industry. We implement the prototype of the proposed scheme for conducting integrated tests. Testin. results of a case study reveal that the proposed scheme ca] efficiently and effectively generating models for identifyin defect beans.Our implementation of the proposed scheme is available a https://github.com/Louis8582/LEGAN.

UR - http://www.scopus.com/inward/record.url?scp=85072953366&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072953366&partnerID=8YFLogxK

U2 - 10.1109/COASE.2019.8843259

DO - 10.1109/COASE.2019.8843259

M3 - Conference contribution

AN - SCOPUS:85072953366

T3 - IEEE International Conference on Automation Science and Engineering

SP - 263

EP - 270

BT - 2019 IEEE 15th International Conference on Automation Science and Engineering, CASE 2019

PB - IEEE Computer Society

ER -

Kuo CJ, Chen CC, Chen TT, Tsai Z, Hung MH, Lin YC et al. A Labor-Efficient GAN-based Model Generation Scheme for Deep-Learning Defect Inspection among Dense Beans in Coffee Industry. In 2019 IEEE 15th International Conference on Automation Science and Engineering, CASE 2019. IEEE Computer Society. 2019. p. 263-270. 8843259. (IEEE International Conference on Automation Science and Engineering). https://doi.org/10.1109/COASE.2019.8843259