Color-based Classification of Dried Cocoa Beans from Various Origins of Indonesia by Image Analysis Using AlexNet and ResNet Architecture-Convolutional Neural Networks
Cocoa plant is widely cultivated in Indonesia and spread across various regions. Diversity in geographical conditions has been known to significantly affect the quality of cocoa beans. Practically, cocoa beans are often mixed without considering the variation in the quality and its origin. This res...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Indonesian Coffee and Cocoa Research Institute
2024-12-01
|
| Series: | Coffee and Cocoa Research Journal |
| Subjects: | |
| Online Access: | https://www.ccrjournal.com/index.php/ccrj/article/view/638 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846100443065745408 |
|---|---|
| author | Wahyu Kristianingsih Bambang Dwi Argo Misnawi Jati Noor Ariefandie Febrianto Yusuf Hendrawan Mochamad Bagus Hermanto Bagus Rahmatullah |
| author_facet | Wahyu Kristianingsih Bambang Dwi Argo Misnawi Jati Noor Ariefandie Febrianto Yusuf Hendrawan Mochamad Bagus Hermanto Bagus Rahmatullah |
| author_sort | Wahyu Kristianingsih |
| collection | DOAJ |
| description |
Cocoa plant is widely cultivated in Indonesia and spread across various regions. Diversity in geographical conditions has been known to significantly affect the quality of cocoa beans. Practically, cocoa beans are often mixed without considering the variation in the quality and its origin. This resulted in reduced global quality and product inconsistency. Improved recognition and classification methods are needed to solve those problems. Non-destructive classification methods can be used to provide a more efficient classification process. The use of artificial intelligence with computer-based deep learning methods was used in this study. Beans samples of various origins (Aceh, Bali, Banten, Yogyakarta, East Kalimantan, West Sulawesi, and West Sumatera) were evaluated. From the
collected samples, 9100 images were then taken for data processing. Data preprocessing included denoising of the background image, cropping, resizing and
changing the storage extension through the training-validation stage and the testing process. AlexNet and ResNet architectures on a Convolutional Neural
Network were used for classification. The results showed that the average accuracy of cocoa image classification based on color identification by computer machines using Alexnet and ResNet was high (99.91% and 99.99%, respectively). This method can be applied to provide more efficient color-based cocoa bean classification for industrial purposes.
|
| format | Article |
| id | doaj-art-54cacf12004b4a95ac34bf3636f1c5de |
| institution | Kabale University |
| issn | 0215-0212 2406-9574 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Indonesian Coffee and Cocoa Research Institute |
| record_format | Article |
| series | Coffee and Cocoa Research Journal |
| spelling | doaj-art-54cacf12004b4a95ac34bf3636f1c5de2024-12-30T06:49:28ZengIndonesian Coffee and Cocoa Research InstituteCoffee and Cocoa Research Journal0215-02122406-95742024-12-0140310.22302/iccri.jur.pelitaperkebunan.v40i3.638Color-based Classification of Dried Cocoa Beans from Various Origins of Indonesia by Image Analysis Using AlexNet and ResNet Architecture-Convolutional Neural NetworksWahyu Kristianingsih0Bambang Dwi Argo1Misnawi Jati2Noor Ariefandie Febrianto3Yusuf Hendrawan4Mochamad Bagus Hermanto5Bagus Rahmatullah61)Department of Agricultural Engineering and Biosystem, Universitas Brawijaya, Jl. Veteran-Malang, IndonesiaDepartment of Agricultural Engineering and Biosystem, Universitas Brawijaya, Jl. Veteran-Malang, IndonesiaIndonesian Coffee and Cocoa Research Institute, Jl. PB Sudirman 90, Jember, IndonesiaIndonesian Coffee and Cocoa Research Institute, Jl. PB Sudirman 90, Jember, IndonesiaDepartment of Agricultural Engineering and Biosystem, Universitas Brawijaya, Jl. Veteran-Malang, IndonesiaDepartment of Agricultural Engineering and Biosystem, Universitas Brawijaya, Jl. Veteran-Malang, IndonesiaDepartment of Agricultural Engineering and Biosystem, Universitas Brawijaya, Jl. Veteran-Malang, Indonesia Cocoa plant is widely cultivated in Indonesia and spread across various regions. Diversity in geographical conditions has been known to significantly affect the quality of cocoa beans. Practically, cocoa beans are often mixed without considering the variation in the quality and its origin. This resulted in reduced global quality and product inconsistency. Improved recognition and classification methods are needed to solve those problems. Non-destructive classification methods can be used to provide a more efficient classification process. The use of artificial intelligence with computer-based deep learning methods was used in this study. Beans samples of various origins (Aceh, Bali, Banten, Yogyakarta, East Kalimantan, West Sulawesi, and West Sumatera) were evaluated. From the collected samples, 9100 images were then taken for data processing. Data preprocessing included denoising of the background image, cropping, resizing and changing the storage extension through the training-validation stage and the testing process. AlexNet and ResNet architectures on a Convolutional Neural Network were used for classification. The results showed that the average accuracy of cocoa image classification based on color identification by computer machines using Alexnet and ResNet was high (99.91% and 99.99%, respectively). This method can be applied to provide more efficient color-based cocoa bean classification for industrial purposes. https://www.ccrjournal.com/index.php/ccrj/article/view/638sortationgradingdeep learningnon-destructiveartificial intelligence |
| spellingShingle | Wahyu Kristianingsih Bambang Dwi Argo Misnawi Jati Noor Ariefandie Febrianto Yusuf Hendrawan Mochamad Bagus Hermanto Bagus Rahmatullah Color-based Classification of Dried Cocoa Beans from Various Origins of Indonesia by Image Analysis Using AlexNet and ResNet Architecture-Convolutional Neural Networks Coffee and Cocoa Research Journal sortation grading deep learning non-destructive artificial intelligence |
| title | Color-based Classification of Dried Cocoa Beans from Various Origins of Indonesia by Image Analysis Using AlexNet and ResNet Architecture-Convolutional Neural Networks |
| title_full | Color-based Classification of Dried Cocoa Beans from Various Origins of Indonesia by Image Analysis Using AlexNet and ResNet Architecture-Convolutional Neural Networks |
| title_fullStr | Color-based Classification of Dried Cocoa Beans from Various Origins of Indonesia by Image Analysis Using AlexNet and ResNet Architecture-Convolutional Neural Networks |
| title_full_unstemmed | Color-based Classification of Dried Cocoa Beans from Various Origins of Indonesia by Image Analysis Using AlexNet and ResNet Architecture-Convolutional Neural Networks |
| title_short | Color-based Classification of Dried Cocoa Beans from Various Origins of Indonesia by Image Analysis Using AlexNet and ResNet Architecture-Convolutional Neural Networks |
| title_sort | color based classification of dried cocoa beans from various origins of indonesia by image analysis using alexnet and resnet architecture convolutional neural networks |
| topic | sortation grading deep learning non-destructive artificial intelligence |
| url | https://www.ccrjournal.com/index.php/ccrj/article/view/638 |
| work_keys_str_mv | AT wahyukristianingsih colorbasedclassificationofdriedcocoabeansfromvariousoriginsofindonesiabyimageanalysisusingalexnetandresnetarchitectureconvolutionalneuralnetworks AT bambangdwiargo colorbasedclassificationofdriedcocoabeansfromvariousoriginsofindonesiabyimageanalysisusingalexnetandresnetarchitectureconvolutionalneuralnetworks AT misnawijati colorbasedclassificationofdriedcocoabeansfromvariousoriginsofindonesiabyimageanalysisusingalexnetandresnetarchitectureconvolutionalneuralnetworks AT noorariefandiefebrianto colorbasedclassificationofdriedcocoabeansfromvariousoriginsofindonesiabyimageanalysisusingalexnetandresnetarchitectureconvolutionalneuralnetworks AT yusufhendrawan colorbasedclassificationofdriedcocoabeansfromvariousoriginsofindonesiabyimageanalysisusingalexnetandresnetarchitectureconvolutionalneuralnetworks AT mochamadbagushermanto colorbasedclassificationofdriedcocoabeansfromvariousoriginsofindonesiabyimageanalysisusingalexnetandresnetarchitectureconvolutionalneuralnetworks AT bagusrahmatullah colorbasedclassificationofdriedcocoabeansfromvariousoriginsofindonesiabyimageanalysisusingalexnetandresnetarchitectureconvolutionalneuralnetworks |