Maize quality detection based on MConv-SwinT high-precision model.
The traditional method of corn quality detection relies heavily on the subjective judgment of inspectors and suffers from a high error rate. To address these issues, this study employs the Swin Transformer as an enhanced base model, integrating machine vision and deep learning techniques for corn qu...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0312363 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575452893413376 |
|---|---|
| author | Ning Zhang Yuanqi Chen Enxu Zhang Ziyang Liu Jie Yue |
| author_facet | Ning Zhang Yuanqi Chen Enxu Zhang Ziyang Liu Jie Yue |
| author_sort | Ning Zhang |
| collection | DOAJ |
| description | The traditional method of corn quality detection relies heavily on the subjective judgment of inspectors and suffers from a high error rate. To address these issues, this study employs the Swin Transformer as an enhanced base model, integrating machine vision and deep learning techniques for corn quality assessment. Initially, images of high-quality, moldy, and broken corn were collected. After preprocessing, a total of 20,152 valid images were obtained for the experimental samples. The network then extracts both shallow and deep features from these maize images, which are subsequently fused. Concurrently, the extracted features undergo further processing through a specially designed convolutional block. The fused features, combined with those processed by the convolutional module, are fed into an attention layer. This attention layer assigns weights to the features, facilitating accurate final classification. Experimental results demonstrate that the MC-Swin Transformer model proposed in this paper significantly outperforms traditional convolutional neural network models in key metrics such as accuracy, precision, recall, and F1 score, achieving a recognition accuracy rate of 99.89%. Thus, the network effectively and efficiently classifies different corn qualities. This study not only offers a novel perspective and technical approach to corn quality detection but also holds significant implications for the advancement of smart agriculture. |
| format | Article |
| id | doaj-art-53fd3930cee74fac834efd7849c26ba3 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-53fd3930cee74fac834efd7849c26ba32025-02-01T05:30:51ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e031236310.1371/journal.pone.0312363Maize quality detection based on MConv-SwinT high-precision model.Ning ZhangYuanqi ChenEnxu ZhangZiyang LiuJie YueThe traditional method of corn quality detection relies heavily on the subjective judgment of inspectors and suffers from a high error rate. To address these issues, this study employs the Swin Transformer as an enhanced base model, integrating machine vision and deep learning techniques for corn quality assessment. Initially, images of high-quality, moldy, and broken corn were collected. After preprocessing, a total of 20,152 valid images were obtained for the experimental samples. The network then extracts both shallow and deep features from these maize images, which are subsequently fused. Concurrently, the extracted features undergo further processing through a specially designed convolutional block. The fused features, combined with those processed by the convolutional module, are fed into an attention layer. This attention layer assigns weights to the features, facilitating accurate final classification. Experimental results demonstrate that the MC-Swin Transformer model proposed in this paper significantly outperforms traditional convolutional neural network models in key metrics such as accuracy, precision, recall, and F1 score, achieving a recognition accuracy rate of 99.89%. Thus, the network effectively and efficiently classifies different corn qualities. This study not only offers a novel perspective and technical approach to corn quality detection but also holds significant implications for the advancement of smart agriculture.https://doi.org/10.1371/journal.pone.0312363 |
| spellingShingle | Ning Zhang Yuanqi Chen Enxu Zhang Ziyang Liu Jie Yue Maize quality detection based on MConv-SwinT high-precision model. PLoS ONE |
| title | Maize quality detection based on MConv-SwinT high-precision model. |
| title_full | Maize quality detection based on MConv-SwinT high-precision model. |
| title_fullStr | Maize quality detection based on MConv-SwinT high-precision model. |
| title_full_unstemmed | Maize quality detection based on MConv-SwinT high-precision model. |
| title_short | Maize quality detection based on MConv-SwinT high-precision model. |
| title_sort | maize quality detection based on mconv swint high precision model |
| url | https://doi.org/10.1371/journal.pone.0312363 |
| work_keys_str_mv | AT ningzhang maizequalitydetectionbasedonmconvswinthighprecisionmodel AT yuanqichen maizequalitydetectionbasedonmconvswinthighprecisionmodel AT enxuzhang maizequalitydetectionbasedonmconvswinthighprecisionmodel AT ziyangliu maizequalitydetectionbasedonmconvswinthighprecisionmodel AT jieyue maizequalitydetectionbasedonmconvswinthighprecisionmodel |