Coffee Maturity Classification Using Convolutional Neural Networks and Transfer Learning
This work presents a framework for coffee maturity classification from multispectral image data based on Convolutional Neural Networks (CNNs). The system leverages the use of multispectral image acquisition systems that generate large amounts of data, by taking advantage of the ability of CNNs to ex...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9755125/ |
| _version_ | 1818193169718706176 |
|---|---|
| author | Manuel Alejandro Tamayo-Monsalve Esteban Mercado-Ruiz Juan Pablo Villa-Pulgarin Mario Alejandro Bravo-Ortiz Harold Brayan Arteaga-Arteaga Alejandro Mora-Rubio Jesus Alejandro Alzate-Grisales Daniel Arias-Garzon Victor Romero-Cano Simon Orozco-Arias Gustavo Gustavo-Osorio Reinel Tabares-Soto |
| author_facet | Manuel Alejandro Tamayo-Monsalve Esteban Mercado-Ruiz Juan Pablo Villa-Pulgarin Mario Alejandro Bravo-Ortiz Harold Brayan Arteaga-Arteaga Alejandro Mora-Rubio Jesus Alejandro Alzate-Grisales Daniel Arias-Garzon Victor Romero-Cano Simon Orozco-Arias Gustavo Gustavo-Osorio Reinel Tabares-Soto |
| author_sort | Manuel Alejandro Tamayo-Monsalve |
| collection | DOAJ |
| description | This work presents a framework for coffee maturity classification from multispectral image data based on Convolutional Neural Networks (CNNs). The system leverages the use of multispectral image acquisition systems that generate large amounts of data, by taking advantage of the ability of CNNs to extract meaningful patterns from very high-dimensional data. We validated the use of five different popular CNN architectures on the classification of cherry coffee fruits according to their ripening stage. The different models were trained on a training dataset balanced in different ways, which resulted in a top accuracy higher than 98% when applied to the classification of 600 coffee fruits in 5 different stages of ripening. This work has the potential of providing the farmer with a high-quality, optimized, accurate and viable method for classifying coffee fruits. In order to foster future research in this area, the data used in this work, which was acquired with a custom-developed multispectral image acquisition system, have been released. |
| first_indexed | 2024-12-12T00:42:08Z |
| format | Article |
| id | doaj.art-e7659e932c444ddf859298bd6cc8d8ed |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-12T00:42:08Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e7659e932c444ddf859298bd6cc8d8ed2022-12-22T00:44:13ZengIEEEIEEE Access2169-35362022-01-0110429714298210.1109/ACCESS.2022.31665159755125Coffee Maturity Classification Using Convolutional Neural Networks and Transfer LearningManuel Alejandro Tamayo-Monsalve0https://orcid.org/0000-0002-9461-733XEsteban Mercado-Ruiz1https://orcid.org/0000-0003-3639-4147Juan Pablo Villa-Pulgarin2https://orcid.org/0000-0003-1263-7618Mario Alejandro Bravo-Ortiz3https://orcid.org/0000-0003-3560-1300Harold Brayan Arteaga-Arteaga4https://orcid.org/0000-0002-2341-5079Alejandro Mora-Rubio5Jesus Alejandro Alzate-Grisales6https://orcid.org/0000-0003-1021-2050Daniel Arias-Garzon7https://orcid.org/0000-0002-0694-012XVictor Romero-Cano8https://orcid.org/0000-0003-2910-5116Simon Orozco-Arias9https://orcid.org/0000-0001-5991-8770Gustavo Gustavo-Osorio10https://orcid.org/0000-0002-8202-6217Reinel Tabares-Soto11https://orcid.org/0000-0002-4978-5211Department of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, ColombiaDepartment of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, ColombiaDepartment of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, ColombiaDepartment of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, ColombiaDepartment of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, ColombiaDepartment of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, ColombiaDepartment of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, ColombiaDepartment of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, ColombiaRobotics and Autonomous Systems Laboratory, Faculty of Engineering, Universidad Autónoma de Occidente, Cali, Valle del Cauca, ColombiaDepartment of Computer Science, Universidad Autónoma de Manizales, Manizales, Caldas, ColombiaDepartment of Electrical, Electronic and Computation, Universidad Nacional de Colombia sede Manizales, Manizales, Caldas, ColombiaDepartment of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, ColombiaThis work presents a framework for coffee maturity classification from multispectral image data based on Convolutional Neural Networks (CNNs). The system leverages the use of multispectral image acquisition systems that generate large amounts of data, by taking advantage of the ability of CNNs to extract meaningful patterns from very high-dimensional data. We validated the use of five different popular CNN architectures on the classification of cherry coffee fruits according to their ripening stage. The different models were trained on a training dataset balanced in different ways, which resulted in a top accuracy higher than 98% when applied to the classification of 600 coffee fruits in 5 different stages of ripening. This work has the potential of providing the farmer with a high-quality, optimized, accurate and viable method for classifying coffee fruits. In order to foster future research in this area, the data used in this work, which was acquired with a custom-developed multispectral image acquisition system, have been released.https://ieeexplore.ieee.org/document/9755125/Coffee maturity classificationconvolutional neural networkdata augmentationdeep learningmultispectral imagestransfer learning |
| spellingShingle | Manuel Alejandro Tamayo-Monsalve Esteban Mercado-Ruiz Juan Pablo Villa-Pulgarin Mario Alejandro Bravo-Ortiz Harold Brayan Arteaga-Arteaga Alejandro Mora-Rubio Jesus Alejandro Alzate-Grisales Daniel Arias-Garzon Victor Romero-Cano Simon Orozco-Arias Gustavo Gustavo-Osorio Reinel Tabares-Soto Coffee Maturity Classification Using Convolutional Neural Networks and Transfer Learning IEEE Access Coffee maturity classification convolutional neural network data augmentation deep learning multispectral images transfer learning |
| title | Coffee Maturity Classification Using Convolutional Neural Networks and Transfer Learning |
| title_full | Coffee Maturity Classification Using Convolutional Neural Networks and Transfer Learning |
| title_fullStr | Coffee Maturity Classification Using Convolutional Neural Networks and Transfer Learning |
| title_full_unstemmed | Coffee Maturity Classification Using Convolutional Neural Networks and Transfer Learning |
| title_short | Coffee Maturity Classification Using Convolutional Neural Networks and Transfer Learning |
| title_sort | coffee maturity classification using convolutional neural networks and transfer learning |
| topic | Coffee maturity classification convolutional neural network data augmentation deep learning multispectral images transfer learning |
| url | https://ieeexplore.ieee.org/document/9755125/ |
| work_keys_str_mv | AT manuelalejandrotamayomonsalve coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT estebanmercadoruiz coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT juanpablovillapulgarin coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT marioalejandrobravoortiz coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT haroldbrayanarteagaarteaga coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT alejandromorarubio coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT jesusalejandroalzategrisales coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT danielariasgarzon coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT victorromerocano coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT simonorozcoarias coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT gustavogustavoosorio coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning AT reineltabaressoto coffeematurityclassificationusingconvolutionalneuralnetworksandtransferlearning |