Research on SPAD Inversion of Rice Leaves at a Field Scale Based on Machine Vision and Leaf Segmentation Techniques
Crop chlorophyll contents affect growth, and accurate assessment aids field management. SPAD (Soil Plant Analysis Development) values of leaves were mainly used to estimate chlorophyll content. Background interference affects the accuracy of SPAD value inversion. To address this issue, a rice leaf S...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/12/1270 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839655128667258880 |
|---|---|
| author | Bailin Yue Yong Jin Shangrong Wu Jieyang Tan Youxing Chen Hu Zhong Guipeng Chen Yingbin Deng |
| author_facet | Bailin Yue Yong Jin Shangrong Wu Jieyang Tan Youxing Chen Hu Zhong Guipeng Chen Yingbin Deng |
| author_sort | Bailin Yue |
| collection | DOAJ |
| description | Crop chlorophyll contents affect growth, and accurate assessment aids field management. SPAD (Soil Plant Analysis Development) values of leaves were mainly used to estimate chlorophyll content. Background interference affects the accuracy of SPAD value inversion. To address this issue, a rice leaf SPAD inversion method combining deep learning and feature selection is proposed. First, a leaf segmentation model based on U-Net was established. Then, the color features of leaf images were extracted. Seven color features highly correlated with SPAD were selected via the Pearson correlation coefficient and recursive feature elimination optimization. Finally, leaf SPAD inversion models based on random forest, support vector regression, BPNNs, and XGBoost were established. The results demonstrated that the U-Net could achieve accurate segmentation of leaves with a maximum mean intersection over union (MIoU) of 88.23. The coefficients of determination R<sup>2</sup> between the anticipated and observed SPAD values of the four models were 0.819, 0.829, 0.896, and 0.721, and the root mean square errors (RMSEs) were 2.223, 2.131, 1.564, and 2.906. Through comparison, the method can accurately predict SPAD in different low-definition and saturation images, showing a certain robustness. It can offer technical support for accurate, nondestructive, and expedited evaluation of crop leaves’ chlorophyll content via machine vision. |
| format | Article |
| id | doaj-art-3d0de70b852c48a1b67d2fc5f9d40d02 |
| institution | Matheson Library |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-3d0de70b852c48a1b67d2fc5f9d40d022025-06-25T13:19:44ZengMDPI AGAgriculture2077-04722025-06-011512127010.3390/agriculture15121270Research on SPAD Inversion of Rice Leaves at a Field Scale Based on Machine Vision and Leaf Segmentation TechniquesBailin Yue0Yong Jin1Shangrong Wu2Jieyang Tan3Youxing Chen4Hu Zhong5Guipeng Chen6Yingbin Deng7School of Information and Communication Engineering, North University of China, Taiyuan 030051, ChinaSchool of Information and Communication Engineering, North University of China, Taiyuan 030051, ChinaState Key Laboratory of Efficient Utilization of Arable Land in China, The Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaInstitute of Agricultural Economics and Information, Hunan Academy of Agricultural Sciences, Changsha 410125, ChinaSchool of Information and Communication Engineering, North University of China, Taiyuan 030051, ChinaState Key Laboratory of Efficient Utilization of Arable Land in China, The Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaInstitute of Agricultural Economics and Information, Jiangxi Academy of Agricultural Sciences, Nanchang 330200, ChinaGuangzhou Institute of Geography, Guangdong Academy of Sciences, Guangzhou 510070, ChinaCrop chlorophyll contents affect growth, and accurate assessment aids field management. SPAD (Soil Plant Analysis Development) values of leaves were mainly used to estimate chlorophyll content. Background interference affects the accuracy of SPAD value inversion. To address this issue, a rice leaf SPAD inversion method combining deep learning and feature selection is proposed. First, a leaf segmentation model based on U-Net was established. Then, the color features of leaf images were extracted. Seven color features highly correlated with SPAD were selected via the Pearson correlation coefficient and recursive feature elimination optimization. Finally, leaf SPAD inversion models based on random forest, support vector regression, BPNNs, and XGBoost were established. The results demonstrated that the U-Net could achieve accurate segmentation of leaves with a maximum mean intersection over union (MIoU) of 88.23. The coefficients of determination R<sup>2</sup> between the anticipated and observed SPAD values of the four models were 0.819, 0.829, 0.896, and 0.721, and the root mean square errors (RMSEs) were 2.223, 2.131, 1.564, and 2.906. Through comparison, the method can accurately predict SPAD in different low-definition and saturation images, showing a certain robustness. It can offer technical support for accurate, nondestructive, and expedited evaluation of crop leaves’ chlorophyll content via machine vision.https://www.mdpi.com/2077-0472/15/12/1270SPAD inversionmachine visionleaf segmentationU-Net network modelfeature optimization |
| spellingShingle | Bailin Yue Yong Jin Shangrong Wu Jieyang Tan Youxing Chen Hu Zhong Guipeng Chen Yingbin Deng Research on SPAD Inversion of Rice Leaves at a Field Scale Based on Machine Vision and Leaf Segmentation Techniques Agriculture SPAD inversion machine vision leaf segmentation U-Net network model feature optimization |
| title | Research on SPAD Inversion of Rice Leaves at a Field Scale Based on Machine Vision and Leaf Segmentation Techniques |
| title_full | Research on SPAD Inversion of Rice Leaves at a Field Scale Based on Machine Vision and Leaf Segmentation Techniques |
| title_fullStr | Research on SPAD Inversion of Rice Leaves at a Field Scale Based on Machine Vision and Leaf Segmentation Techniques |
| title_full_unstemmed | Research on SPAD Inversion of Rice Leaves at a Field Scale Based on Machine Vision and Leaf Segmentation Techniques |
| title_short | Research on SPAD Inversion of Rice Leaves at a Field Scale Based on Machine Vision and Leaf Segmentation Techniques |
| title_sort | research on spad inversion of rice leaves at a field scale based on machine vision and leaf segmentation techniques |
| topic | SPAD inversion machine vision leaf segmentation U-Net network model feature optimization |
| url | https://www.mdpi.com/2077-0472/15/12/1270 |
| work_keys_str_mv | AT bailinyue researchonspadinversionofriceleavesatafieldscalebasedonmachinevisionandleafsegmentationtechniques AT yongjin researchonspadinversionofriceleavesatafieldscalebasedonmachinevisionandleafsegmentationtechniques AT shangrongwu researchonspadinversionofriceleavesatafieldscalebasedonmachinevisionandleafsegmentationtechniques AT jieyangtan researchonspadinversionofriceleavesatafieldscalebasedonmachinevisionandleafsegmentationtechniques AT youxingchen researchonspadinversionofriceleavesatafieldscalebasedonmachinevisionandleafsegmentationtechniques AT huzhong researchonspadinversionofriceleavesatafieldscalebasedonmachinevisionandleafsegmentationtechniques AT guipengchen researchonspadinversionofriceleavesatafieldscalebasedonmachinevisionandleafsegmentationtechniques AT yingbindeng researchonspadinversionofriceleavesatafieldscalebasedonmachinevisionandleafsegmentationtechniques |