A quality grade classification method for fresh tea leaves based on an improved YOLOv8x-SPPCSPC-CBAM model
Abstract In light of the prevalent issues concerning the mechanical grading of fresh tea leaves, characterized by high damage rates and poor accuracy, as well as the limited grading precision through the integration of machine vision and machine learning (ML) algorithms, this study presents an innov...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-54389-y |
| _version_ | 1797274797973962752 |
|---|---|
| author | Xiu’yan Zhao Yu’xiang He Hong’tao Zhang Zhao’tang Ding Chang’an Zhou Kai’xing Zhang |
| author_facet | Xiu’yan Zhao Yu’xiang He Hong’tao Zhang Zhao’tang Ding Chang’an Zhou Kai’xing Zhang |
| author_sort | Xiu’yan Zhao |
| collection | DOAJ |
| description | Abstract In light of the prevalent issues concerning the mechanical grading of fresh tea leaves, characterized by high damage rates and poor accuracy, as well as the limited grading precision through the integration of machine vision and machine learning (ML) algorithms, this study presents an innovative approach for classifying the quality grade of fresh tea leaves. This approach leverages an integration of image recognition and deep learning (DL) algorithm to accurately classify tea leaves’ grades by identifying distinct bud and leaf combinations. The method begins by acquiring separate images of orderly scattered and randomly stacked fresh tea leaves. These images undergo data augmentation techniques, such as rotation, flipping, and contrast adjustment, to form the scattered and stacked tea leaves datasets. Subsequently, the YOLOv8x model was enhanced by Space pyramid pooling improvements (SPPCSPC) and the concentration-based attention module (CBAM). The established YOLOv8x-SPPCSPC-CBAM model is evaluated by comparing it with popular DL models, including Faster R-CNN, YOLOv5x, and YOLOv8x. The experimental findings reveal that the YOLOv8x-SPPCSPC-CBAM model delivers the most impressive results. For the scattered tea leaves, the mean average precision, precision, recall, and number of images processed per second rates of 98.2%, 95.8%, 96.7%, and 2.77, respectively, while for stacked tea leaves, they are 99.1%, 99.1%, 97.7% and 2.35, respectively. This study provides a robust framework for accurately classifying the quality grade of fresh tea leaves. |
| first_indexed | 2024-03-07T15:04:05Z |
| format | Article |
| id | doaj.art-35a1f17af8a04437a5f1181fcddaf03d |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-07T15:04:05Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-35a1f17af8a04437a5f1181fcddaf03d2024-03-05T18:59:02ZengNature PortfolioScientific Reports2045-23222024-02-0114111310.1038/s41598-024-54389-yA quality grade classification method for fresh tea leaves based on an improved YOLOv8x-SPPCSPC-CBAM modelXiu’yan Zhao0Yu’xiang He1Hong’tao Zhang2Zhao’tang Ding3Chang’an Zhou4Kai’xing Zhang5College of Information Science and Engineering, Shandong Agricultural UniversityCollege of Mechanical and Electronic Engineering, Shandong Agricultural UniversityCollege of Mechanical and Electronic Engineering, Shandong Agricultural UniversityTea Research Institute, Shandong Academy of Agricultural SciencesCollege of Mechanical and Electronic Engineering, Shandong Agricultural UniversityCollege of Mechanical and Electronic Engineering, Shandong Agricultural UniversityAbstract In light of the prevalent issues concerning the mechanical grading of fresh tea leaves, characterized by high damage rates and poor accuracy, as well as the limited grading precision through the integration of machine vision and machine learning (ML) algorithms, this study presents an innovative approach for classifying the quality grade of fresh tea leaves. This approach leverages an integration of image recognition and deep learning (DL) algorithm to accurately classify tea leaves’ grades by identifying distinct bud and leaf combinations. The method begins by acquiring separate images of orderly scattered and randomly stacked fresh tea leaves. These images undergo data augmentation techniques, such as rotation, flipping, and contrast adjustment, to form the scattered and stacked tea leaves datasets. Subsequently, the YOLOv8x model was enhanced by Space pyramid pooling improvements (SPPCSPC) and the concentration-based attention module (CBAM). The established YOLOv8x-SPPCSPC-CBAM model is evaluated by comparing it with popular DL models, including Faster R-CNN, YOLOv5x, and YOLOv8x. The experimental findings reveal that the YOLOv8x-SPPCSPC-CBAM model delivers the most impressive results. For the scattered tea leaves, the mean average precision, precision, recall, and number of images processed per second rates of 98.2%, 95.8%, 96.7%, and 2.77, respectively, while for stacked tea leaves, they are 99.1%, 99.1%, 97.7% and 2.35, respectively. This study provides a robust framework for accurately classifying the quality grade of fresh tea leaves.https://doi.org/10.1038/s41598-024-54389-yFresh tea leavesGrade discriminationTarget detectionImprove YOLOv8xCBAM |
| spellingShingle | Xiu’yan Zhao Yu’xiang He Hong’tao Zhang Zhao’tang Ding Chang’an Zhou Kai’xing Zhang A quality grade classification method for fresh tea leaves based on an improved YOLOv8x-SPPCSPC-CBAM model Scientific Reports Fresh tea leaves Grade discrimination Target detection Improve YOLOv8x CBAM |
| title | A quality grade classification method for fresh tea leaves based on an improved YOLOv8x-SPPCSPC-CBAM model |
| title_full | A quality grade classification method for fresh tea leaves based on an improved YOLOv8x-SPPCSPC-CBAM model |
| title_fullStr | A quality grade classification method for fresh tea leaves based on an improved YOLOv8x-SPPCSPC-CBAM model |
| title_full_unstemmed | A quality grade classification method for fresh tea leaves based on an improved YOLOv8x-SPPCSPC-CBAM model |
| title_short | A quality grade classification method for fresh tea leaves based on an improved YOLOv8x-SPPCSPC-CBAM model |
| title_sort | quality grade classification method for fresh tea leaves based on an improved yolov8x sppcspc cbam model |
| topic | Fresh tea leaves Grade discrimination Target detection Improve YOLOv8x CBAM |
| url | https://doi.org/10.1038/s41598-024-54389-y |
| work_keys_str_mv | AT xiuyanzhao aqualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT yuxianghe aqualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT hongtaozhang aqualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT zhaotangding aqualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT changanzhou aqualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT kaixingzhang aqualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT xiuyanzhao qualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT yuxianghe qualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT hongtaozhang qualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT zhaotangding qualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT changanzhou qualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel AT kaixingzhang qualitygradeclassificationmethodforfreshtealeavesbasedonanimprovedyolov8xsppcspccbammodel |