Evaluation of Convolutional Neural Networks’ Hyperparameters with Transfer Learning to Determine Sorting of Ripe Medjool Dates
Convolutional neural networks (CNNs) have proven their efficiency in various applications in agriculture. In crops such as date, they have been mainly used in the identification and sorting of ripe fruits. The aim of this study was the performance evaluation of eight different CNNs, considering tran...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/11/2/115 |
| _version_ | 1797416970715398144 |
|---|---|
| author | Blanca Dalila Pérez-Pérez Juan Pablo García Vázquez Ricardo Salomón-Torres |
| author_facet | Blanca Dalila Pérez-Pérez Juan Pablo García Vázquez Ricardo Salomón-Torres |
| author_sort | Blanca Dalila Pérez-Pérez |
| collection | DOAJ |
| description | Convolutional neural networks (CNNs) have proven their efficiency in various applications in agriculture. In crops such as date, they have been mainly used in the identification and sorting of ripe fruits. The aim of this study was the performance evaluation of eight different CNNs, considering transfer learning for their training, as well as five hyperparameters. The CNN architectures evaluated were VGG-16, VGG-19, ResNet-50, ResNet-101, ResNet-152, AlexNet, Inception V3, and CNN from scratch. Likewise, the hyperparameters analyzed were the number of layers, the number of epochs, the batch size, optimizer, and learning rate. The accuracy and processing time were considered to determine the performance of CNN architectures, in the classification of mature dates’ cultivar Medjool. The model obtained from VGG-19 architecture with a batch of 128 and Adam optimizer with a learning rate of 0.01 presented the best performance with an accuracy of 99.32%. We concluded that the VGG-19 model can be used to build computer vision systems that help producers improve their sorting process to detect the Tamar stage of a Medjool date. |
| first_indexed | 2024-03-09T06:12:06Z |
| format | Article |
| id | doaj.art-ed54e7af694b461c90062297c1e68fca |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-09T06:12:06Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-ed54e7af694b461c90062297c1e68fca2023-12-03T11:57:31ZengMDPI AGAgriculture2077-04722021-02-0111211510.3390/agriculture11020115Evaluation of Convolutional Neural Networks’ Hyperparameters with Transfer Learning to Determine Sorting of Ripe Medjool DatesBlanca Dalila Pérez-Pérez0Juan Pablo García Vázquez1Ricardo Salomón-Torres2Facultad de Ingeniería, Universidad Autónoma de Baja California (UABC), Mexicali 21100, MexicoFacultad de Ingeniería, Universidad Autónoma de Baja California (UABC), Mexicali 21100, MexicoUnidad Académica San Luis Río Colorado, Universidad Estatal de Sonora (UES), Sonora 83500, MexicoConvolutional neural networks (CNNs) have proven their efficiency in various applications in agriculture. In crops such as date, they have been mainly used in the identification and sorting of ripe fruits. The aim of this study was the performance evaluation of eight different CNNs, considering transfer learning for their training, as well as five hyperparameters. The CNN architectures evaluated were VGG-16, VGG-19, ResNet-50, ResNet-101, ResNet-152, AlexNet, Inception V3, and CNN from scratch. Likewise, the hyperparameters analyzed were the number of layers, the number of epochs, the batch size, optimizer, and learning rate. The accuracy and processing time were considered to determine the performance of CNN architectures, in the classification of mature dates’ cultivar Medjool. The model obtained from VGG-19 architecture with a batch of 128 and Adam optimizer with a learning rate of 0.01 presented the best performance with an accuracy of 99.32%. We concluded that the VGG-19 model can be used to build computer vision systems that help producers improve their sorting process to detect the Tamar stage of a Medjool date.https://www.mdpi.com/2077-0472/11/2/115<i>Phoenix dactylifera</i> L.Medjool datesimage classificationconvolutional neural networksdeep learningtransfer learning |
| spellingShingle | Blanca Dalila Pérez-Pérez Juan Pablo García Vázquez Ricardo Salomón-Torres Evaluation of Convolutional Neural Networks’ Hyperparameters with Transfer Learning to Determine Sorting of Ripe Medjool Dates Agriculture <i>Phoenix dactylifera</i> L. Medjool dates image classification convolutional neural networks deep learning transfer learning |
| title | Evaluation of Convolutional Neural Networks’ Hyperparameters with Transfer Learning to Determine Sorting of Ripe Medjool Dates |
| title_full | Evaluation of Convolutional Neural Networks’ Hyperparameters with Transfer Learning to Determine Sorting of Ripe Medjool Dates |
| title_fullStr | Evaluation of Convolutional Neural Networks’ Hyperparameters with Transfer Learning to Determine Sorting of Ripe Medjool Dates |
| title_full_unstemmed | Evaluation of Convolutional Neural Networks’ Hyperparameters with Transfer Learning to Determine Sorting of Ripe Medjool Dates |
| title_short | Evaluation of Convolutional Neural Networks’ Hyperparameters with Transfer Learning to Determine Sorting of Ripe Medjool Dates |
| title_sort | evaluation of convolutional neural networks hyperparameters with transfer learning to determine sorting of ripe medjool dates |
| topic | <i>Phoenix dactylifera</i> L. Medjool dates image classification convolutional neural networks deep learning transfer learning |
| url | https://www.mdpi.com/2077-0472/11/2/115 |
| work_keys_str_mv | AT blancadalilaperezperez evaluationofconvolutionalneuralnetworkshyperparameterswithtransferlearningtodeterminesortingofripemedjooldates AT juanpablogarciavazquez evaluationofconvolutionalneuralnetworkshyperparameterswithtransferlearningtodeterminesortingofripemedjooldates AT ricardosalomontorres evaluationofconvolutionalneuralnetworkshyperparameterswithtransferlearningtodeterminesortingofripemedjooldates |