Deep-Learning-Based Defective Bean Inspection with GAN-Structured Automated Labeled Data Augmentation in Coffee Industry
In the production process from green beans to coffee bean packages, the defective bean removal (or in short, defect removal) is one of most labor-consuming stages, and many companies investigate the automation of this stage for minimizing human efforts. In this paper, we propose a deep-learning-base...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/19/4166 |
| _version_ | 1828422759769702400 |
|---|---|
| author | Yung-Chien Chou Cheng-Ju Kuo Tzu-Ting Chen Gwo-Jiun Horng Mao-Yuan Pai Mu-En Wu Yu-Chuan Lin Min-Hsiung Hung Wei-Tsung Su Yi-Chung Chen Ding-Chau Wang Chao-Chun Chen |
| author_facet | Yung-Chien Chou Cheng-Ju Kuo Tzu-Ting Chen Gwo-Jiun Horng Mao-Yuan Pai Mu-En Wu Yu-Chuan Lin Min-Hsiung Hung Wei-Tsung Su Yi-Chung Chen Ding-Chau Wang Chao-Chun Chen |
| author_sort | Yung-Chien Chou |
| collection | DOAJ |
| description | In the production process from green beans to coffee bean packages, the defective bean removal (or in short, defect removal) is one of most labor-consuming stages, and many companies investigate the automation of this stage for minimizing human efforts. In this paper, we propose a deep-learning-based defective bean inspection scheme (DL-DBIS), together with a GAN (generative-adversarial network)-structured automated labeled data augmentation method (GALDAM) for enhancing the proposed scheme, so that the automation degree of bean removal with robotic arms can be further improved for coffee industries. The proposed scheme is aimed at providing an effective model to a deep-learning-based object detection module for accurately identifying defects among dense beans. The proposed GALDAM can be used to greatly reduce labor costs, since the data labeling is the most labor-intensive work in this sort of solutions. Our proposed scheme brings two main impacts to intelligent agriculture. First, our proposed scheme is can be easily adopted by industries as human effort in labeling coffee beans are minimized. The users can easily customize their own defective bean model without spending a great amount of time on labeling small and dense objects. Second, our scheme can inspect all classes of defective beans categorized by the SCAA (Specialty Coffee Association of America) at the same time and can be easily extended if more classes of defective beans are added. These two advantages increase the degree of automation in the coffee industry. The prototype of the proposed scheme was developed for studying integrated tests. Testing results of a case study reveal that the proposed scheme can efficiently and effectively generate models for identifying defective beans with accuracy and precision values up to <inline-formula> <math display="inline"> <semantics> <mrow> <mn>80</mn> <mo>%</mo> </mrow> </semantics> </math> </inline-formula>. |
| first_indexed | 2024-12-10T15:52:32Z |
| format | Article |
| id | doaj.art-9471a34168994c32bf752a8df1fa0849 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-10T15:52:32Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9471a34168994c32bf752a8df1fa08492022-12-22T01:42:46ZengMDPI AGApplied Sciences2076-34172019-10-01919416610.3390/app9194166app9194166Deep-Learning-Based Defective Bean Inspection with GAN-Structured Automated Labeled Data Augmentation in Coffee IndustryYung-Chien Chou0Cheng-Ju Kuo1Tzu-Ting Chen2Gwo-Jiun Horng3Mao-Yuan Pai4Mu-En Wu5Yu-Chuan Lin6Min-Hsiung Hung7Wei-Tsung Su8Yi-Chung Chen9Ding-Chau Wang10Chao-Chun Chen11Institute of Manufacturing Information and systems, Department of Computer Science & Information Engineering, National Cheng Kung University, Tainan 701, TaiwanInstitute of Manufacturing Information and systems, Department of Computer Science & Information Engineering, National Cheng Kung University, Tainan 701, TaiwanInstitute of Manufacturing Information and systems, Department of Computer Science & Information Engineering, National Cheng Kung University, Tainan 701, TaiwanDepartment of Computer Science & Information Engineering, Department of Management Information System, Southern Taiwan University of Science and Technology, Tainan 710, TaiwanGeneral Research Service Center, National Pingtung University of Science and Technology, Pingtung 912, TaiwanDepartment of Information & Financial Management, National Taipei University of Technology, Taipei 106, TaiwanInstitute of Manufacturing Information and systems, Department of Computer Science & Information Engineering, National Cheng Kung University, Tainan 701, TaiwanDepartment of Computer Science & Information Engineering, Chinese Culture University, Taipei 111, TaiwanDepartment of Computer Science & Information Engineering, Aletheia University, New Taipei 251, TaiwanDepartment of Industrial Engineering & Management, National Yunlin University of Science and Technology, Yunlin 640, TaiwanDepartment of Computer Science & Information Engineering, Department of Management Information System, Southern Taiwan University of Science and Technology, Tainan 710, TaiwanInstitute of Manufacturing Information and systems, Department of Computer Science & Information Engineering, National Cheng Kung University, Tainan 701, TaiwanIn the production process from green beans to coffee bean packages, the defective bean removal (or in short, defect removal) is one of most labor-consuming stages, and many companies investigate the automation of this stage for minimizing human efforts. In this paper, we propose a deep-learning-based defective bean inspection scheme (DL-DBIS), together with a GAN (generative-adversarial network)-structured automated labeled data augmentation method (GALDAM) for enhancing the proposed scheme, so that the automation degree of bean removal with robotic arms can be further improved for coffee industries. The proposed scheme is aimed at providing an effective model to a deep-learning-based object detection module for accurately identifying defects among dense beans. The proposed GALDAM can be used to greatly reduce labor costs, since the data labeling is the most labor-intensive work in this sort of solutions. Our proposed scheme brings two main impacts to intelligent agriculture. First, our proposed scheme is can be easily adopted by industries as human effort in labeling coffee beans are minimized. The users can easily customize their own defective bean model without spending a great amount of time on labeling small and dense objects. Second, our scheme can inspect all classes of defective beans categorized by the SCAA (Specialty Coffee Association of America) at the same time and can be easily extended if more classes of defective beans are added. These two advantages increase the degree of automation in the coffee industry. The prototype of the proposed scheme was developed for studying integrated tests. Testing results of a case study reveal that the proposed scheme can efficiently and effectively generate models for identifying defective beans with accuracy and precision values up to <inline-formula> <math display="inline"> <semantics> <mrow> <mn>80</mn> <mo>%</mo> </mrow> </semantics> </math> </inline-formula>.https://www.mdpi.com/2076-3417/9/19/4166automatic defect inspectionmachine learningsmart agricultureautomation engineeringdata augmentationapplied artificial intelligencegan optimizer |
| spellingShingle | Yung-Chien Chou Cheng-Ju Kuo Tzu-Ting Chen Gwo-Jiun Horng Mao-Yuan Pai Mu-En Wu Yu-Chuan Lin Min-Hsiung Hung Wei-Tsung Su Yi-Chung Chen Ding-Chau Wang Chao-Chun Chen Deep-Learning-Based Defective Bean Inspection with GAN-Structured Automated Labeled Data Augmentation in Coffee Industry Applied Sciences automatic defect inspection machine learning smart agriculture automation engineering data augmentation applied artificial intelligence gan optimizer |
| title | Deep-Learning-Based Defective Bean Inspection with GAN-Structured Automated Labeled Data Augmentation in Coffee Industry |
| title_full | Deep-Learning-Based Defective Bean Inspection with GAN-Structured Automated Labeled Data Augmentation in Coffee Industry |
| title_fullStr | Deep-Learning-Based Defective Bean Inspection with GAN-Structured Automated Labeled Data Augmentation in Coffee Industry |
| title_full_unstemmed | Deep-Learning-Based Defective Bean Inspection with GAN-Structured Automated Labeled Data Augmentation in Coffee Industry |
| title_short | Deep-Learning-Based Defective Bean Inspection with GAN-Structured Automated Labeled Data Augmentation in Coffee Industry |
| title_sort | deep learning based defective bean inspection with gan structured automated labeled data augmentation in coffee industry |
| topic | automatic defect inspection machine learning smart agriculture automation engineering data augmentation applied artificial intelligence gan optimizer |
| url | https://www.mdpi.com/2076-3417/9/19/4166 |
| work_keys_str_mv | AT yungchienchou deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT chengjukuo deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT tzutingchen deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT gwojiunhorng deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT maoyuanpai deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT muenwu deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT yuchuanlin deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT minhsiunghung deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT weitsungsu deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT yichungchen deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT dingchauwang deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry AT chaochunchen deeplearningbaseddefectivebeaninspectionwithganstructuredautomatedlabeleddataaugmentationincoffeeindustry |