Feature Normalization Reweighting Regression Network for Sugar Content Measurement of Grapes
The measurement of grape sugar content is an important index for classifying grapes based on their quality. Owing to the correlation between grape sugar content and appearance, non-destructive measurements are possible using computer vision and deep learning. This study investigates the quality clas...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/15/7474 |
| _version_ | 1797442971411415040 |
|---|---|
| author | Mei Jia Jiuliang Li Tianyang Hu Yingzhe Jiang Jun Luo |
| author_facet | Mei Jia Jiuliang Li Tianyang Hu Yingzhe Jiang Jun Luo |
| author_sort | Mei Jia |
| collection | DOAJ |
| description | The measurement of grape sugar content is an important index for classifying grapes based on their quality. Owing to the correlation between grape sugar content and appearance, non-destructive measurements are possible using computer vision and deep learning. This study investigates the quality classification of the Red Globe grape. The number of collected grapes in the range of the 15~16% measure is three times more than in the range of <14% or in the range of the >18% measure. This study presents a framework named feature normalization reweighting regression (FNRR) to address this imbalanced distribution of sugar content of the grape datasets. The experimental results show that the FNRR framework can measure the sugar content of a whole bunch of grapes with high accuracy using typical convolution neural networks and a visual transformer model. Specifically, the visual transformer model achieved the best accuracy with a balanced loss function, with the coefficient of determination R = 0.9599 and the root mean squared error RMSE = 0.3841%. The results show that the effect of the visual transformer model is better than that of the convolutional neural network. The research findings also indicate that the visual transformer model based on the proposed framework can accurately predict the sugar content of grapes, non-destructive evaluation of grape quality, and could provide reference values for grape harvesting. |
| first_indexed | 2024-03-09T12:49:22Z |
| format | Article |
| id | doaj.art-bdccf0692d1b452e85250860aee6906e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T12:49:22Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-bdccf0692d1b452e85250860aee6906e2023-11-30T22:08:53ZengMDPI AGApplied Sciences2076-34172022-07-011215747410.3390/app12157474Feature Normalization Reweighting Regression Network for Sugar Content Measurement of GrapesMei Jia0Jiuliang Li1Tianyang Hu2Yingzhe Jiang3Jun Luo4College of informatics, Huazhong Agricultural University, Wuhan 430070, ChinaCollege of informatics, Huazhong Agricultural University, Wuhan 430070, ChinaCollege of informatics, Huazhong Agricultural University, Wuhan 430070, ChinaCollege of informatics, Huazhong Agricultural University, Wuhan 430070, ChinaCollege of informatics, Huazhong Agricultural University, Wuhan 430070, ChinaThe measurement of grape sugar content is an important index for classifying grapes based on their quality. Owing to the correlation between grape sugar content and appearance, non-destructive measurements are possible using computer vision and deep learning. This study investigates the quality classification of the Red Globe grape. The number of collected grapes in the range of the 15~16% measure is three times more than in the range of <14% or in the range of the >18% measure. This study presents a framework named feature normalization reweighting regression (FNRR) to address this imbalanced distribution of sugar content of the grape datasets. The experimental results show that the FNRR framework can measure the sugar content of a whole bunch of grapes with high accuracy using typical convolution neural networks and a visual transformer model. Specifically, the visual transformer model achieved the best accuracy with a balanced loss function, with the coefficient of determination R = 0.9599 and the root mean squared error RMSE = 0.3841%. The results show that the effect of the visual transformer model is better than that of the convolutional neural network. The research findings also indicate that the visual transformer model based on the proposed framework can accurately predict the sugar content of grapes, non-destructive evaluation of grape quality, and could provide reference values for grape harvesting.https://www.mdpi.com/2076-3417/12/15/7474grape sugar contentregressionfeature normalization reweighting regressionconvolution neural networkvisual transformer |
| spellingShingle | Mei Jia Jiuliang Li Tianyang Hu Yingzhe Jiang Jun Luo Feature Normalization Reweighting Regression Network for Sugar Content Measurement of Grapes Applied Sciences grape sugar content regression feature normalization reweighting regression convolution neural network visual transformer |
| title | Feature Normalization Reweighting Regression Network for Sugar Content Measurement of Grapes |
| title_full | Feature Normalization Reweighting Regression Network for Sugar Content Measurement of Grapes |
| title_fullStr | Feature Normalization Reweighting Regression Network for Sugar Content Measurement of Grapes |
| title_full_unstemmed | Feature Normalization Reweighting Regression Network for Sugar Content Measurement of Grapes |
| title_short | Feature Normalization Reweighting Regression Network for Sugar Content Measurement of Grapes |
| title_sort | feature normalization reweighting regression network for sugar content measurement of grapes |
| topic | grape sugar content regression feature normalization reweighting regression convolution neural network visual transformer |
| url | https://www.mdpi.com/2076-3417/12/15/7474 |
| work_keys_str_mv | AT meijia featurenormalizationreweightingregressionnetworkforsugarcontentmeasurementofgrapes AT jiuliangli featurenormalizationreweightingregressionnetworkforsugarcontentmeasurementofgrapes AT tianyanghu featurenormalizationreweightingregressionnetworkforsugarcontentmeasurementofgrapes AT yingzhejiang featurenormalizationreweightingregressionnetworkforsugarcontentmeasurementofgrapes AT junluo featurenormalizationreweightingregressionnetworkforsugarcontentmeasurementofgrapes |