Discrimination of foreign bodies in quinoa (Chenopodium quinoa Willd.) grains using convolutional neural networks with a transfer learning approach
The rising interest in quinoa (Chenopodium quinoa Willd.) is due to its high protein content and gluten-free condition; nonetheless, the presence of foreign bodies in quinoa processing facilities is an issue that must be addressed. As a result, convolutional neural networks have been adopted, mostly...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2023-01-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/14808.pdf |
| _version_ | 1827610843358953472 |
|---|---|
| author | Himer Avila-George Miguel De-la-Torre Jorge Sánchez-Garcés Joel Jerson Coaquira Quispe Jose Manuel Prieto Wilson Castro |
| author_facet | Himer Avila-George Miguel De-la-Torre Jorge Sánchez-Garcés Joel Jerson Coaquira Quispe Jose Manuel Prieto Wilson Castro |
| author_sort | Himer Avila-George |
| collection | DOAJ |
| description | The rising interest in quinoa (Chenopodium quinoa Willd.) is due to its high protein content and gluten-free condition; nonetheless, the presence of foreign bodies in quinoa processing facilities is an issue that must be addressed. As a result, convolutional neural networks have been adopted, mostly because of their data extraction capabilities, which had not been utilized before for this purpose. Consequently, the main objective of this work is to evaluate convolutional neural networks with a learning transfer for foreign bodies identification in quinoa samples. For experimentation, quinoa samples were collected and manually split into 17 classes: quinoa grains and 16 foreign bodies. Then, one thousand images were obtained from each class in RGB space and transformed into four different color spaces (L*a*b*, HSV, YCbCr, and Gray). Three convolutional neural networks (AlexNet, MobileNetv2, and DenseNet-201) were trained using the five color spaces, and the evaluation results were expressed in terms of accuracy and F-score. All the CNN approaches compared showed an F-score ranging from 98% to 99%; both color space and CNN structure were found to have significant effects on the F-score. Also, DenseNet-201 was the most robust architecture and, at the same time, the most time-consuming. These results evidence the capacity of CNN architectures to be used for the discrimination of foreign bodies in quinoa processing facilities. |
| first_indexed | 2024-03-09T07:57:35Z |
| format | Article |
| id | doaj.art-6f25d4c98a754b6caee759141792f11f |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T07:57:35Z |
| publishDate | 2023-01-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-6f25d4c98a754b6caee759141792f11f2023-12-03T00:55:37ZengPeerJ Inc.PeerJ2167-83592023-01-0111e1480810.7717/peerj.14808Discrimination of foreign bodies in quinoa (Chenopodium quinoa Willd.) grains using convolutional neural networks with a transfer learning approachHimer Avila-George0Miguel De-la-Torre1Jorge Sánchez-Garcés2Joel Jerson Coaquira Quispe3Jose Manuel Prieto4Wilson Castro5Departamento de Ciencias Computacionales e Ingenierías, Universidad de Guadalajara, Ameca, Jalisco, MéxicoDepartamento de Ciencias Computacionales e Ingenierías, Universidad de Guadalajara, Ameca, Jalisco, MéxicoFacultad de Ingeniería y Arquitectura, Universidad Peruana Unión, Juliaca, Puno, PerúFacultad de Ingeniería y Arquitectura, Universidad Peruana Unión, Juliaca, Puno, PerúFacultad de Ingeniería y Arquitectura, Universidad Peruana Unión, Juliaca, Puno, PerúFacultad de Ingeniería en Industrias Alimentarias, Universidad Nacional de Frontera, Sullana, Piura, PerúThe rising interest in quinoa (Chenopodium quinoa Willd.) is due to its high protein content and gluten-free condition; nonetheless, the presence of foreign bodies in quinoa processing facilities is an issue that must be addressed. As a result, convolutional neural networks have been adopted, mostly because of their data extraction capabilities, which had not been utilized before for this purpose. Consequently, the main objective of this work is to evaluate convolutional neural networks with a learning transfer for foreign bodies identification in quinoa samples. For experimentation, quinoa samples were collected and manually split into 17 classes: quinoa grains and 16 foreign bodies. Then, one thousand images were obtained from each class in RGB space and transformed into four different color spaces (L*a*b*, HSV, YCbCr, and Gray). Three convolutional neural networks (AlexNet, MobileNetv2, and DenseNet-201) were trained using the five color spaces, and the evaluation results were expressed in terms of accuracy and F-score. All the CNN approaches compared showed an F-score ranging from 98% to 99%; both color space and CNN structure were found to have significant effects on the F-score. Also, DenseNet-201 was the most robust architecture and, at the same time, the most time-consuming. These results evidence the capacity of CNN architectures to be used for the discrimination of foreign bodies in quinoa processing facilities.https://peerj.com/articles/14808.pdfQuinoaPost-harvestDeep learningImage processingDiscriminationTransfer learning |
| spellingShingle | Himer Avila-George Miguel De-la-Torre Jorge Sánchez-Garcés Joel Jerson Coaquira Quispe Jose Manuel Prieto Wilson Castro Discrimination of foreign bodies in quinoa (Chenopodium quinoa Willd.) grains using convolutional neural networks with a transfer learning approach PeerJ Quinoa Post-harvest Deep learning Image processing Discrimination Transfer learning |
| title | Discrimination of foreign bodies in quinoa (Chenopodium quinoa Willd.) grains using convolutional neural networks with a transfer learning approach |
| title_full | Discrimination of foreign bodies in quinoa (Chenopodium quinoa Willd.) grains using convolutional neural networks with a transfer learning approach |
| title_fullStr | Discrimination of foreign bodies in quinoa (Chenopodium quinoa Willd.) grains using convolutional neural networks with a transfer learning approach |
| title_full_unstemmed | Discrimination of foreign bodies in quinoa (Chenopodium quinoa Willd.) grains using convolutional neural networks with a transfer learning approach |
| title_short | Discrimination of foreign bodies in quinoa (Chenopodium quinoa Willd.) grains using convolutional neural networks with a transfer learning approach |
| title_sort | discrimination of foreign bodies in quinoa chenopodium quinoa willd grains using convolutional neural networks with a transfer learning approach |
| topic | Quinoa Post-harvest Deep learning Image processing Discrimination Transfer learning |
| url | https://peerj.com/articles/14808.pdf |
| work_keys_str_mv | AT himeravilageorge discriminationofforeignbodiesinquinoachenopodiumquinoawilldgrainsusingconvolutionalneuralnetworkswithatransferlearningapproach AT migueldelatorre discriminationofforeignbodiesinquinoachenopodiumquinoawilldgrainsusingconvolutionalneuralnetworkswithatransferlearningapproach AT jorgesanchezgarces discriminationofforeignbodiesinquinoachenopodiumquinoawilldgrainsusingconvolutionalneuralnetworkswithatransferlearningapproach AT joeljersoncoaquiraquispe discriminationofforeignbodiesinquinoachenopodiumquinoawilldgrainsusingconvolutionalneuralnetworkswithatransferlearningapproach AT josemanuelprieto discriminationofforeignbodiesinquinoachenopodiumquinoawilldgrainsusingconvolutionalneuralnetworkswithatransferlearningapproach AT wilsoncastro discriminationofforeignbodiesinquinoachenopodiumquinoawilldgrainsusingconvolutionalneuralnetworkswithatransferlearningapproach |