Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques
ObjectiveTo realize rapid and accurate measurement of both internal and external quality of tomatoes, and improve the efficiency and quality of tomato grading.MethodsBased on machine vision and spectroscopy technology, proposed a tomato comprehensive quality grading method which combined external an...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Editorial Office of Food and Machinery
2024-09-01
|
| Series: | Shipin yu jixie |
| Subjects: | |
| Online Access: | http://www.ifoodmm.com/spyjx/article/abstract/20240918?st=article_issue |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850052749493796864 |
|---|---|
| author | GUO Dechao RAO Yuanli ZHANG Hao LI Chunfeng ZHAO Qiang |
| author_facet | GUO Dechao RAO Yuanli ZHANG Hao LI Chunfeng ZHAO Qiang |
| author_sort | GUO Dechao |
| collection | DOAJ |
| description | ObjectiveTo realize rapid and accurate measurement of both internal and external quality of tomatoes, and improve the efficiency and quality of tomato grading.MethodsBased on machine vision and spectroscopy technology, proposed a tomato comprehensive quality grading method which combined external and internal quality. By optimizing the YOLOv8 model in four aspects (lightweight convolution, small object detection layer, CBAM attention mechanism, and loss function), external defect detection was completed, and external quality grading was achieved by combining fruit shape index and tomato size. Complete tomato internal quality grading through preprocessing methods, feature extraction methods, and improved particle swarm optimization using least squares support vector machine. Analyzed the performance of the proposed grading detection method through experiments.ResultsThe proposed method could achieve comprehensive quality testing of tomatoes with high accuracy and efficiency. The accuracy of external quality grading >93.00%, the accuracy of internal quality grading >86.00%, the accuracy of fusion quality grading >96.00%, and the average grading time <0.25 s.ConclusionCombining machine vision and spectral detection technology can achieve rapid, non-destructive, and accurate evaluation of tomato comprehensive quality. |
| format | Article |
| id | doaj-art-4e6a09ed6ed5450da22a3512d6d934e4 |
| institution | DOAJ |
| issn | 1003-5788 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | The Editorial Office of Food and Machinery |
| record_format | Article |
| series | Shipin yu jixie |
| spelling | doaj-art-4e6a09ed6ed5450da22a3512d6d934e42025-08-20T02:52:43ZengThe Editorial Office of Food and MachineryShipin yu jixie1003-57882024-09-0140912313010.13652/j.spjx.1003.5788.2024.600901003-5788（2024）09-0123-08Comprehensive quality detection method for tomatoes combining machine vision and spectral techniquesGUO Dechao0RAO Yuanli1ZHANG Hao2LI Chunfeng3ZHAO Qiang4Guangzhou University of Chinese Medicine, Guangzhou, Guangdong510006, ChinaGuangzhou University of Chinese Medicine, Guangzhou, Guangdong510006, ChinaGuangzhou Center for Disease Control and Prevention, Guangzhou, Guangdong510440, ChinaGuangdong University of Technology, Guangzhou, Guangdong510006, ChinaSouth China Agricultural University, Guangzhou, Guangdong510642, ChinaObjectiveTo realize rapid and accurate measurement of both internal and external quality of tomatoes, and improve the efficiency and quality of tomato grading.MethodsBased on machine vision and spectroscopy technology, proposed a tomato comprehensive quality grading method which combined external and internal quality. By optimizing the YOLOv8 model in four aspects (lightweight convolution, small object detection layer, CBAM attention mechanism, and loss function), external defect detection was completed, and external quality grading was achieved by combining fruit shape index and tomato size. Complete tomato internal quality grading through preprocessing methods, feature extraction methods, and improved particle swarm optimization using least squares support vector machine. Analyzed the performance of the proposed grading detection method through experiments.ResultsThe proposed method could achieve comprehensive quality testing of tomatoes with high accuracy and efficiency. The accuracy of external quality grading >93.00%, the accuracy of internal quality grading >86.00%, the accuracy of fusion quality grading >96.00%, and the average grading time <0.25 s.ConclusionCombining machine vision and spectral detection technology can achieve rapid, non-destructive, and accurate evaluation of tomato comprehensive quality.http://www.ifoodmm.com/spyjx/article/abstract/20240918?st=article_issuetomatoesquality gradingmachine visionspectral technologyyolov8 modelleast squares support vector machine |
| spellingShingle | GUO Dechao RAO Yuanli ZHANG Hao LI Chunfeng ZHAO Qiang Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques Shipin yu jixie tomatoes quality grading machine vision spectral technology yolov8 model least squares support vector machine |
| title | Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques |
| title_full | Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques |
| title_fullStr | Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques |
| title_full_unstemmed | Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques |
| title_short | Comprehensive quality detection method for tomatoes combining machine vision and spectral techniques |
| title_sort | comprehensive quality detection method for tomatoes combining machine vision and spectral techniques |
| topic | tomatoes quality grading machine vision spectral technology yolov8 model least squares support vector machine |
| url | http://www.ifoodmm.com/spyjx/article/abstract/20240918?st=article_issue |
| work_keys_str_mv | AT guodechao comprehensivequalitydetectionmethodfortomatoescombiningmachinevisionandspectraltechniques AT raoyuanli comprehensivequalitydetectionmethodfortomatoescombiningmachinevisionandspectraltechniques AT zhanghao comprehensivequalitydetectionmethodfortomatoescombiningmachinevisionandspectraltechniques AT lichunfeng comprehensivequalitydetectionmethodfortomatoescombiningmachinevisionandspectraltechniques AT zhaoqiang comprehensivequalitydetectionmethodfortomatoescombiningmachinevisionandspectraltechniques |