Detection of weeds in vegetables using image classification neural networks and image processing
Weed management presents a major challenge to vegetable growth. Accurate identification of weeds is essential for automated weeding. However, the wide variety of weed types and their complex distribution creates difficulties in rapid and accurate weed detection. In this study, instead of directly ap...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Physics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2025.1496778/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585083022737408 |
|---|---|
| author | Huiping Jin Kang Han Kang Han Hongting Xia Bo Xu Xiaojun Jin |
| author_facet | Huiping Jin Kang Han Kang Han Hongting Xia Bo Xu Xiaojun Jin |
| author_sort | Huiping Jin |
| collection | DOAJ |
| description | Weed management presents a major challenge to vegetable growth. Accurate identification of weeds is essential for automated weeding. However, the wide variety of weed types and their complex distribution creates difficulties in rapid and accurate weed detection. In this study, instead of directly applying deep learning to identify weeds, we first created grid cells on the input images. Image classification neural networks were utilized to identify the grid cells containing vegetables and exclude them from further analysis. Finally, image processing technology was employed to segment the non-vegetable grid images based on their color features. The background grid cells, which contained no green pixels, were identified, while the remaining cells were labeled as weed cells. EfficientNet, GoogLeNet, and ResNet models achieved overall accuracies of over 0.956 in identifying vegetables in the testing dataset, demonstrating exceptional identification performance. Among these models, the ResNet model exhibited the highest computational efficiency, with a classification time of 12.76 ms per image and a corresponding frame rate of 80.31 fps, satisfying the requirement for real-time weed detection. Effectively identifying vegetables and differentiating weeds from soil significantly reduces the complexity of weed detection and improves its accuracy. |
| format | Article |
| id | doaj-art-98956ee3a11242a889949bc770527e08 |
| institution | Kabale University |
| issn | 2296-424X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physics |
| spelling | doaj-art-98956ee3a11242a889949bc770527e082025-01-27T05:14:38ZengFrontiers Media S.A.Frontiers in Physics2296-424X2025-01-011310.3389/fphy.2025.14967781496778Detection of weeds in vegetables using image classification neural networks and image processingHuiping Jin0Kang Han1Kang Han2Hongting Xia3Bo Xu4Xiaojun Jin5Engineering Training Center, Nanjing Forestry University, Nanjing, Jiangsu, ChinaPeking University Institute of Advanced Agricultural Sciences, Shandong Laboratory of Advanced Agricultural Sciences in Weifang, Weifang, Shandong, ChinaJurong Institute of Smart Agriculture, Zhenjiang, Jiangsu, ChinaJurong Institute of Smart Agriculture, Zhenjiang, Jiangsu, ChinaEngineering Training Center, Nanjing Forestry University, Nanjing, Jiangsu, ChinaPeking University Institute of Advanced Agricultural Sciences, Shandong Laboratory of Advanced Agricultural Sciences in Weifang, Weifang, Shandong, ChinaWeed management presents a major challenge to vegetable growth. Accurate identification of weeds is essential for automated weeding. However, the wide variety of weed types and their complex distribution creates difficulties in rapid and accurate weed detection. In this study, instead of directly applying deep learning to identify weeds, we first created grid cells on the input images. Image classification neural networks were utilized to identify the grid cells containing vegetables and exclude them from further analysis. Finally, image processing technology was employed to segment the non-vegetable grid images based on their color features. The background grid cells, which contained no green pixels, were identified, while the remaining cells were labeled as weed cells. EfficientNet, GoogLeNet, and ResNet models achieved overall accuracies of over 0.956 in identifying vegetables in the testing dataset, demonstrating exceptional identification performance. Among these models, the ResNet model exhibited the highest computational efficiency, with a classification time of 12.76 ms per image and a corresponding frame rate of 80.31 fps, satisfying the requirement for real-time weed detection. Effectively identifying vegetables and differentiating weeds from soil significantly reduces the complexity of weed detection and improves its accuracy.https://www.frontiersin.org/articles/10.3389/fphy.2025.1496778/fullweed detectiondeep learningimage classification neural networksimage processingweed management |
| spellingShingle | Huiping Jin Kang Han Kang Han Hongting Xia Bo Xu Xiaojun Jin Detection of weeds in vegetables using image classification neural networks and image processing Frontiers in Physics weed detection deep learning image classification neural networks image processing weed management |
| title | Detection of weeds in vegetables using image classification neural networks and image processing |
| title_full | Detection of weeds in vegetables using image classification neural networks and image processing |
| title_fullStr | Detection of weeds in vegetables using image classification neural networks and image processing |
| title_full_unstemmed | Detection of weeds in vegetables using image classification neural networks and image processing |
| title_short | Detection of weeds in vegetables using image classification neural networks and image processing |
| title_sort | detection of weeds in vegetables using image classification neural networks and image processing |
| topic | weed detection deep learning image classification neural networks image processing weed management |
| url | https://www.frontiersin.org/articles/10.3389/fphy.2025.1496778/full |
| work_keys_str_mv | AT huipingjin detectionofweedsinvegetablesusingimageclassificationneuralnetworksandimageprocessing AT kanghan detectionofweedsinvegetablesusingimageclassificationneuralnetworksandimageprocessing AT kanghan detectionofweedsinvegetablesusingimageclassificationneuralnetworksandimageprocessing AT hongtingxia detectionofweedsinvegetablesusingimageclassificationneuralnetworksandimageprocessing AT boxu detectionofweedsinvegetablesusingimageclassificationneuralnetworksandimageprocessing AT xiaojunjin detectionofweedsinvegetablesusingimageclassificationneuralnetworksandimageprocessing |