Lightweight Non-Destructive Detection of Diseased Apples Based on Structural Re-Parameterization Technique
This study addresses the challenges in the non-destructive detection of diseased apples, specifically the high complexity and poor real-time performance of the classification model for detecting diseased fruits in apple grading. Research is conducted on a lightweight model for apple defect recogniti...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/5/1907 |
| _version_ | 1827319840565624832 |
|---|---|
| author | Bo Han Ziao Lu Luan Dong Jingjing Zhang |
| author_facet | Bo Han Ziao Lu Luan Dong Jingjing Zhang |
| author_sort | Bo Han |
| collection | DOAJ |
| description | This study addresses the challenges in the non-destructive detection of diseased apples, specifically the high complexity and poor real-time performance of the classification model for detecting diseased fruits in apple grading. Research is conducted on a lightweight model for apple defect recognition, and an improved VEW-YOLOv8n method is proposed. The backbone network incorporates a lightweight, re-parameterization VanillaC2f module, reducing both complexity and the number of parameters, and it employs an extended activation function to enhance the model’s nonlinear expression capability. In the neck network, an Efficient-Neck lightweight structure, developed using the lightweight modules and augmented with a channel shuffling strategy, decreases the computational load while ensuring comprehensive feature information fusion. The model’s robustness and generalization ability are further enhanced by employing the WIoU bounding box loss function, evaluating the quality of anchor frames using outlier metrics, and incorporating a dynamically updated gradient gain assignment strategy. Experimental results indicate that the improved model surpasses the YOLOv8n model, achieving a 2.7% increase in average accuracy, a 24.3% reduction in parameters, a 28.0% decrease in computational volume, and an 8.5% improvement in inference speed. This technology offers a novel, effective method for the non-destructive detection of diseased fruits in apple grading working procedures. |
| first_indexed | 2024-04-25T00:35:24Z |
| format | Article |
| id | doaj.art-6349b32a25964876a41198a134cbc0ec |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-25T00:35:24Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-6349b32a25964876a41198a134cbc0ec2024-03-12T16:39:25ZengMDPI AGApplied Sciences2076-34172024-02-01145190710.3390/app14051907Lightweight Non-Destructive Detection of Diseased Apples Based on Structural Re-Parameterization TechniqueBo Han0Ziao Lu1Luan Dong2Jingjing Zhang3College of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, ChinaCollege of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, ChinaCollege of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, ChinaCollege of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, ChinaThis study addresses the challenges in the non-destructive detection of diseased apples, specifically the high complexity and poor real-time performance of the classification model for detecting diseased fruits in apple grading. Research is conducted on a lightweight model for apple defect recognition, and an improved VEW-YOLOv8n method is proposed. The backbone network incorporates a lightweight, re-parameterization VanillaC2f module, reducing both complexity and the number of parameters, and it employs an extended activation function to enhance the model’s nonlinear expression capability. In the neck network, an Efficient-Neck lightweight structure, developed using the lightweight modules and augmented with a channel shuffling strategy, decreases the computational load while ensuring comprehensive feature information fusion. The model’s robustness and generalization ability are further enhanced by employing the WIoU bounding box loss function, evaluating the quality of anchor frames using outlier metrics, and incorporating a dynamically updated gradient gain assignment strategy. Experimental results indicate that the improved model surpasses the YOLOv8n model, achieving a 2.7% increase in average accuracy, a 24.3% reduction in parameters, a 28.0% decrease in computational volume, and an 8.5% improvement in inference speed. This technology offers a novel, effective method for the non-destructive detection of diseased fruits in apple grading working procedures.https://www.mdpi.com/2076-3417/14/5/1907artificial intelligencenon-destructive detectiondiseased appleslightweightYOLOv8 |
| spellingShingle | Bo Han Ziao Lu Luan Dong Jingjing Zhang Lightweight Non-Destructive Detection of Diseased Apples Based on Structural Re-Parameterization Technique Applied Sciences artificial intelligence non-destructive detection diseased apples lightweight YOLOv8 |
| title | Lightweight Non-Destructive Detection of Diseased Apples Based on Structural Re-Parameterization Technique |
| title_full | Lightweight Non-Destructive Detection of Diseased Apples Based on Structural Re-Parameterization Technique |
| title_fullStr | Lightweight Non-Destructive Detection of Diseased Apples Based on Structural Re-Parameterization Technique |
| title_full_unstemmed | Lightweight Non-Destructive Detection of Diseased Apples Based on Structural Re-Parameterization Technique |
| title_short | Lightweight Non-Destructive Detection of Diseased Apples Based on Structural Re-Parameterization Technique |
| title_sort | lightweight non destructive detection of diseased apples based on structural re parameterization technique |
| topic | artificial intelligence non-destructive detection diseased apples lightweight YOLOv8 |
| url | https://www.mdpi.com/2076-3417/14/5/1907 |
| work_keys_str_mv | AT bohan lightweightnondestructivedetectionofdiseasedapplesbasedonstructuralreparameterizationtechnique AT ziaolu lightweightnondestructivedetectionofdiseasedapplesbasedonstructuralreparameterizationtechnique AT luandong lightweightnondestructivedetectionofdiseasedapplesbasedonstructuralreparameterizationtechnique AT jingjingzhang lightweightnondestructivedetectionofdiseasedapplesbasedonstructuralreparameterizationtechnique |