Convolutional neural network model for the qualitative evaluation of geometric shape of carrot root
The main objective of the study is the development of an automatic carrot root classification model, marked as CR-NET, with the use of a Convolutional Neural Network (CNN). CNN with a constant architecture was built, consisting of an alternating arrangement of five Conv2D, MaxPooling2D and Dropout...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Scientific Agricultural Society of Finland
2024-03-01
|
| Series: | Agricultural and Food Science |
| Online Access: | https://journal.fi/afs/article/view/135986 |
| _version_ | 1797254420745945088 |
|---|---|
| author | Piotr Rybacki Zuzanna Sawinska Miroslava Kačániová Przemysław Ł. Kowalczewski Andrzej Osuch Karol Durczak |
| author_facet | Piotr Rybacki Zuzanna Sawinska Miroslava Kačániová Przemysław Ł. Kowalczewski Andrzej Osuch Karol Durczak |
| author_sort | Piotr Rybacki |
| collection | DOAJ |
| description |
The main objective of the study is the development of an automatic carrot root classification model, marked as CR-NET, with the use of a Convolutional Neural Network (CNN). CNN with a constant architecture was built, consisting
of an alternating arrangement of five Conv2D, MaxPooling2D and Dropout classes, for which in the Python 3.9
programming language a calculation algorithm was developed. It was found that the classification process of the carrot root images was carried out with an accuracy of 89.06%, meaning that 50 images were misclassified. The highest number of 21 erroneously classified photographs were from the extra class, of which 15 to the first class, thus not resulting in significant loss. However, assuming the number of refuse as the classification basis, the model accuracy greatly increases to 98.69%, as only 6 photographs were erroneously assigned.
|
| first_indexed | 2024-04-24T21:49:41Z |
| format | Article |
| id | doaj.art-1366478791a9410589d6a27661a7ff85 |
| institution | Directory Open Access Journal |
| issn | 1459-6067 1795-1895 |
| language | English |
| last_indexed | 2024-04-24T21:49:41Z |
| publishDate | 2024-03-01 |
| publisher | Scientific Agricultural Society of Finland |
| record_format | Article |
| series | Agricultural and Food Science |
| spelling | doaj.art-1366478791a9410589d6a27661a7ff852024-03-20T16:23:16ZengScientific Agricultural Society of FinlandAgricultural and Food Science1459-60671795-18952024-03-0110.23986/afsci.135986Convolutional neural network model for the qualitative evaluation of geometric shape of carrot rootPiotr Rybacki0Zuzanna Sawinska1Miroslava Kačániová2Przemysław Ł. Kowalczewski3Andrzej Osuch4Karol Durczak5Poznan University of Life Sciences, PolandPoznan University of Life Sciences, PolandSlovak University of Agriculture, SlovakiaPoznań University of Life Sciences, PolandPoznań University of Life Sciences, PolandPoznań University of Life Sciences, Poland The main objective of the study is the development of an automatic carrot root classification model, marked as CR-NET, with the use of a Convolutional Neural Network (CNN). CNN with a constant architecture was built, consisting of an alternating arrangement of five Conv2D, MaxPooling2D and Dropout classes, for which in the Python 3.9 programming language a calculation algorithm was developed. It was found that the classification process of the carrot root images was carried out with an accuracy of 89.06%, meaning that 50 images were misclassified. The highest number of 21 erroneously classified photographs were from the extra class, of which 15 to the first class, thus not resulting in significant loss. However, assuming the number of refuse as the classification basis, the model accuracy greatly increases to 98.69%, as only 6 photographs were erroneously assigned. https://journal.fi/afs/article/view/135986 |
| spellingShingle | Piotr Rybacki Zuzanna Sawinska Miroslava Kačániová Przemysław Ł. Kowalczewski Andrzej Osuch Karol Durczak Convolutional neural network model for the qualitative evaluation of geometric shape of carrot root Agricultural and Food Science |
| title | Convolutional neural network model for the qualitative evaluation of geometric shape of carrot root |
| title_full | Convolutional neural network model for the qualitative evaluation of geometric shape of carrot root |
| title_fullStr | Convolutional neural network model for the qualitative evaluation of geometric shape of carrot root |
| title_full_unstemmed | Convolutional neural network model for the qualitative evaluation of geometric shape of carrot root |
| title_short | Convolutional neural network model for the qualitative evaluation of geometric shape of carrot root |
| title_sort | convolutional neural network model for the qualitative evaluation of geometric shape of carrot root |
| url | https://journal.fi/afs/article/view/135986 |
| work_keys_str_mv | AT piotrrybacki convolutionalneuralnetworkmodelforthequalitativeevaluationofgeometricshapeofcarrotroot AT zuzannasawinska convolutionalneuralnetworkmodelforthequalitativeevaluationofgeometricshapeofcarrotroot AT miroslavakacaniova convolutionalneuralnetworkmodelforthequalitativeevaluationofgeometricshapeofcarrotroot AT przemysławłkowalczewski convolutionalneuralnetworkmodelforthequalitativeevaluationofgeometricshapeofcarrotroot AT andrzejosuch convolutionalneuralnetworkmodelforthequalitativeevaluationofgeometricshapeofcarrotroot AT karoldurczak convolutionalneuralnetworkmodelforthequalitativeevaluationofgeometricshapeofcarrotroot |