Evaluation of Rice Degree of Milling Based on Bayesian Optimization and Multi-Scale Residual Model
Traditional machine learning-based methods for the detection of rice degree of milling (DOM) that are not comprehensive in feature extraction and have low recognition rates fail to meet the demand for fast, non-destructive, and accurate detection. This paper presents a digital image processing techn...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Foods |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-8158/11/22/3720 |
| _version_ | 1797465313990672384 |
|---|---|
| author | Weidong Chen Wanyu Li Ying Wang |
| author_facet | Weidong Chen Wanyu Li Ying Wang |
| author_sort | Weidong Chen |
| collection | DOAJ |
| description | Traditional machine learning-based methods for the detection of rice degree of milling (DOM) that are not comprehensive in feature extraction and have low recognition rates fail to meet the demand for fast, non-destructive, and accurate detection. This paper presents a digital image processing technology combined with deep learning to implement the classification of DOM of rice. An improved multi-scale information fusion model of the InceptionResNet–Bayesian optimization algorithm (IRBOA) was constructed based on the Inception-v3 structure and residual network (ResNet) model. It enables to automatically extract more comprehensive features of rice and determine the DOM of rice. Additionally, the important hyperparameters in the model were tuned by the BOA to optimize the recognition rate of rice DOM. The results show the hyperparameters optimized using the BOA are those that would not be chosen in manual tuning. The classification precision of the IRBOA model reached 99.22%, 94.92%, and 96.55% for well-milled, reasonably well-milled, and substandard rice, respectively, with an average accuracy of no less than 96.90%. This model improved 7.41% over the traditional machine learning model and at least 1.35% over the fashionable CNN model with strong generalization performance. This method effectively completes rapid, non-destructive, and accurate intelligent detection of rice DOM, which can supply a reliable and accurate technical mean for rice processing enterprises to guide the rice processing process. |
| first_indexed | 2024-03-09T18:19:47Z |
| format | Article |
| id | doaj.art-977e0e0645974f3abc9a3256cee2079b |
| institution | Directory Open Access Journal |
| issn | 2304-8158 |
| language | English |
| last_indexed | 2024-03-09T18:19:47Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj.art-977e0e0645974f3abc9a3256cee2079b2023-11-24T08:23:14ZengMDPI AGFoods2304-81582022-11-011122372010.3390/foods11223720Evaluation of Rice Degree of Milling Based on Bayesian Optimization and Multi-Scale Residual ModelWeidong Chen0Wanyu Li1Ying Wang2College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, ChinaCollege of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, ChinaCollege of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, ChinaTraditional machine learning-based methods for the detection of rice degree of milling (DOM) that are not comprehensive in feature extraction and have low recognition rates fail to meet the demand for fast, non-destructive, and accurate detection. This paper presents a digital image processing technology combined with deep learning to implement the classification of DOM of rice. An improved multi-scale information fusion model of the InceptionResNet–Bayesian optimization algorithm (IRBOA) was constructed based on the Inception-v3 structure and residual network (ResNet) model. It enables to automatically extract more comprehensive features of rice and determine the DOM of rice. Additionally, the important hyperparameters in the model were tuned by the BOA to optimize the recognition rate of rice DOM. The results show the hyperparameters optimized using the BOA are those that would not be chosen in manual tuning. The classification precision of the IRBOA model reached 99.22%, 94.92%, and 96.55% for well-milled, reasonably well-milled, and substandard rice, respectively, with an average accuracy of no less than 96.90%. This model improved 7.41% over the traditional machine learning model and at least 1.35% over the fashionable CNN model with strong generalization performance. This method effectively completes rapid, non-destructive, and accurate intelligent detection of rice DOM, which can supply a reliable and accurate technical mean for rice processing enterprises to guide the rice processing process.https://www.mdpi.com/2304-8158/11/22/3720degree of millingmulti-scale information fusionresidual network modelBayesian optimization algorithm |
| spellingShingle | Weidong Chen Wanyu Li Ying Wang Evaluation of Rice Degree of Milling Based on Bayesian Optimization and Multi-Scale Residual Model Foods degree of milling multi-scale information fusion residual network model Bayesian optimization algorithm |
| title | Evaluation of Rice Degree of Milling Based on Bayesian Optimization and Multi-Scale Residual Model |
| title_full | Evaluation of Rice Degree of Milling Based on Bayesian Optimization and Multi-Scale Residual Model |
| title_fullStr | Evaluation of Rice Degree of Milling Based on Bayesian Optimization and Multi-Scale Residual Model |
| title_full_unstemmed | Evaluation of Rice Degree of Milling Based on Bayesian Optimization and Multi-Scale Residual Model |
| title_short | Evaluation of Rice Degree of Milling Based on Bayesian Optimization and Multi-Scale Residual Model |
| title_sort | evaluation of rice degree of milling based on bayesian optimization and multi scale residual model |
| topic | degree of milling multi-scale information fusion residual network model Bayesian optimization algorithm |
| url | https://www.mdpi.com/2304-8158/11/22/3720 |
| work_keys_str_mv | AT weidongchen evaluationofricedegreeofmillingbasedonbayesianoptimizationandmultiscaleresidualmodel AT wanyuli evaluationofricedegreeofmillingbasedonbayesianoptimizationandmultiscaleresidualmodel AT yingwang evaluationofricedegreeofmillingbasedonbayesianoptimizationandmultiscaleresidualmodel |