Detection storage time of mild bruise’s yellow peaches using the combined hyperspectral imaging and machine learning method
Abstract To deduce the process of bruise and reduce the number of bruised fruits from the source, the storage time of yellow peaches after bruise should be identified. In order to distinguish the different storage times of mild bruise’s yellow peaches more effectively than current detection methods,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-07-01
|
| Series: | Journal of Analytical Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40543-022-00334-5 |
| _version_ | 1828426805190590464 |
|---|---|
| author | Bin Li Hai Yin Yan-de Liu Feng Zhang A.-kun Yang Cheng-tao Su Ai-guo Ou-yang |
| author_facet | Bin Li Hai Yin Yan-de Liu Feng Zhang A.-kun Yang Cheng-tao Su Ai-guo Ou-yang |
| author_sort | Bin Li |
| collection | DOAJ |
| description | Abstract To deduce the process of bruise and reduce the number of bruised fruits from the source, the storage time of yellow peaches after bruise should be identified. In order to distinguish the different storage times of mild bruise’s yellow peaches more effectively than current detection methods, the combined hyperspectral imaging and machine learning method was proposed. Firstly, the sample bruise region spectrum was extracted as spectral features, and then, the hyperspectral images were processed by Principal Component Analysis (PCA), and eight single-wavelength images were selected according to the weight coefficient curve of PC1 images, and the gray values of the selected images were calculated as image features. Finally, in order to find the optimal discriminative model, random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost) models were built based on spectral features, image features, and spectral features combined with image features, respectively. The results show that the XGBoost models based on spectral features, image features, and spectral features combined with image features are the optimal models with the overall accuracy of 77.50%, 87.50% and 90.00%, respectively. To simplify the model, Competitive Adaptive Reweighted Sampling (CARS) algorithm was used to screen the wavelength of the normalized spectral data, and then they were fused with the image feature data again and the XGBoost model with an overall model accuracy of 95.00% was built. To sum up, the combined hyperspectral imaging and machine learning method can be used to distinguish the different storage times (2 h, 8 h, 24 h and 48 h) of mild bruise’s yellow peaches effectively. It provides a certain theoretical basis for hyperspectral imaging technology in fruit bruise detection. |
| first_indexed | 2024-12-10T16:51:44Z |
| format | Article |
| id | doaj.art-e4ba24e9dd264b378911f7da07918b12 |
| institution | Directory Open Access Journal |
| issn | 2093-3371 |
| language | English |
| last_indexed | 2024-12-10T16:51:44Z |
| publishDate | 2022-07-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Analytical Science and Technology |
| spelling | doaj.art-e4ba24e9dd264b378911f7da07918b122022-12-22T01:40:52ZengSpringerOpenJournal of Analytical Science and Technology2093-33712022-07-0113111210.1186/s40543-022-00334-5Detection storage time of mild bruise’s yellow peaches using the combined hyperspectral imaging and machine learning methodBin Li0Hai Yin1Yan-de Liu2Feng Zhang3A.-kun Yang4Cheng-tao Su5Ai-guo Ou-yang6Institute of Optical-Electro-Mechatronics Technology and Application, East China Jiao Tong University, National and Local Joint Engineering Research Center of Fruit Intelligent Photoelectric Detection Technology and EquipmentInstitute of Optical-Electro-Mechatronics Technology and Application, East China Jiao Tong University, National and Local Joint Engineering Research Center of Fruit Intelligent Photoelectric Detection Technology and EquipmentInstitute of Optical-Electro-Mechatronics Technology and Application, East China Jiao Tong University, National and Local Joint Engineering Research Center of Fruit Intelligent Photoelectric Detection Technology and EquipmentInstitute of Optical-Electro-Mechatronics Technology and Application, East China Jiao Tong University, National and Local Joint Engineering Research Center of Fruit Intelligent Photoelectric Detection Technology and EquipmentInstitute of Optical-Electro-Mechatronics Technology and Application, East China Jiao Tong University, National and Local Joint Engineering Research Center of Fruit Intelligent Photoelectric Detection Technology and EquipmentInstitute of Optical-Electro-Mechatronics Technology and Application, East China Jiao Tong University, National and Local Joint Engineering Research Center of Fruit Intelligent Photoelectric Detection Technology and EquipmentInstitute of Optical-Electro-Mechatronics Technology and Application, East China Jiao Tong University, National and Local Joint Engineering Research Center of Fruit Intelligent Photoelectric Detection Technology and EquipmentAbstract To deduce the process of bruise and reduce the number of bruised fruits from the source, the storage time of yellow peaches after bruise should be identified. In order to distinguish the different storage times of mild bruise’s yellow peaches more effectively than current detection methods, the combined hyperspectral imaging and machine learning method was proposed. Firstly, the sample bruise region spectrum was extracted as spectral features, and then, the hyperspectral images were processed by Principal Component Analysis (PCA), and eight single-wavelength images were selected according to the weight coefficient curve of PC1 images, and the gray values of the selected images were calculated as image features. Finally, in order to find the optimal discriminative model, random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost) models were built based on spectral features, image features, and spectral features combined with image features, respectively. The results show that the XGBoost models based on spectral features, image features, and spectral features combined with image features are the optimal models with the overall accuracy of 77.50%, 87.50% and 90.00%, respectively. To simplify the model, Competitive Adaptive Reweighted Sampling (CARS) algorithm was used to screen the wavelength of the normalized spectral data, and then they were fused with the image feature data again and the XGBoost model with an overall model accuracy of 95.00% was built. To sum up, the combined hyperspectral imaging and machine learning method can be used to distinguish the different storage times (2 h, 8 h, 24 h and 48 h) of mild bruise’s yellow peaches effectively. It provides a certain theoretical basis for hyperspectral imaging technology in fruit bruise detection.https://doi.org/10.1186/s40543-022-00334-5Hyperspectral imagingYellow peachesImage featuresSpectral featuresMild bruiseStorage time |
| spellingShingle | Bin Li Hai Yin Yan-de Liu Feng Zhang A.-kun Yang Cheng-tao Su Ai-guo Ou-yang Detection storage time of mild bruise’s yellow peaches using the combined hyperspectral imaging and machine learning method Journal of Analytical Science and Technology Hyperspectral imaging Yellow peaches Image features Spectral features Mild bruise Storage time |
| title | Detection storage time of mild bruise’s yellow peaches using the combined hyperspectral imaging and machine learning method |
| title_full | Detection storage time of mild bruise’s yellow peaches using the combined hyperspectral imaging and machine learning method |
| title_fullStr | Detection storage time of mild bruise’s yellow peaches using the combined hyperspectral imaging and machine learning method |
| title_full_unstemmed | Detection storage time of mild bruise’s yellow peaches using the combined hyperspectral imaging and machine learning method |
| title_short | Detection storage time of mild bruise’s yellow peaches using the combined hyperspectral imaging and machine learning method |
| title_sort | detection storage time of mild bruise s yellow peaches using the combined hyperspectral imaging and machine learning method |
| topic | Hyperspectral imaging Yellow peaches Image features Spectral features Mild bruise Storage time |
| url | https://doi.org/10.1186/s40543-022-00334-5 |
| work_keys_str_mv | AT binli detectionstoragetimeofmildbruisesyellowpeachesusingthecombinedhyperspectralimagingandmachinelearningmethod AT haiyin detectionstoragetimeofmildbruisesyellowpeachesusingthecombinedhyperspectralimagingandmachinelearningmethod AT yandeliu detectionstoragetimeofmildbruisesyellowpeachesusingthecombinedhyperspectralimagingandmachinelearningmethod AT fengzhang detectionstoragetimeofmildbruisesyellowpeachesusingthecombinedhyperspectralimagingandmachinelearningmethod AT akunyang detectionstoragetimeofmildbruisesyellowpeachesusingthecombinedhyperspectralimagingandmachinelearningmethod AT chengtaosu detectionstoragetimeofmildbruisesyellowpeachesusingthecombinedhyperspectralimagingandmachinelearningmethod AT aiguoouyang detectionstoragetimeofmildbruisesyellowpeachesusingthecombinedhyperspectralimagingandmachinelearningmethod |