Frontiers in Plant SciencePub Date : 2025-01-22eCollection Date: 2024-01-01DOI: 10.3389/fpls.2024.1501612
Bing Shi, Luqi Guo, Lejun Yu
{"title":"Accurate LAI estimation of soybean plants in the field using deep learning and clustering algorithms.","authors":"Bing Shi, Luqi Guo, Lejun Yu","doi":"10.3389/fpls.2024.1501612","DOIUrl":"10.3389/fpls.2024.1501612","url":null,"abstract":"<p><p>The leaf area index (LAI) is a critical parameter for characterizing plant foliage abundance, canopy structure changes, and vegetation productivity in ecosystems. Traditional phenological measurements are often destructive, time-consuming, and labor-intensive. This paper proposes a high-throughput 3D point cloud data processing pipeline to segment field soybean plants and estimate their LAI. The 3D point cloud data is obtained from a UAV equipped with a LiDAR camera. First, The PointNet++ model was applied to simplify the segmentation process by isolating field soybean plants from their surroundings and eliminating environmental complexities. Subsequently, individual segmentation was achieved using the Watershed approach and k-means clustering algorithms, segmenting the field soybeans into individual plants. Finally, the LAI of soybean plant was estimated using a machine learning method and validated against measured values. The PointNet++ model improved segmentation accuracy by 6.73%, and the watershed algorithm achieved F1 scores of 0.89-0.90, outperforming k-means in complex adhesion cases. For LAI estimation, the SVM model showed the highest accuracy (R² = 0.79, RMSE = 0.47), with RF and XGBoost also performing well (R² > 0.69, RMSE< 0.65). This indicates that the individual segmentation algorithm, Watershed-based approach combined with PointNet++, can serve as a crucial foundation for extracting high-throughput plant phenotypic data. The experimental results confirm that the proposed method can rapidly calculate the morphological parameters of each soybean plant, making it suitable for high-throughput soybean phenotyping.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1501612"},"PeriodicalIF":4.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11794303/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143254449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Study on improving yield and antioxidant enzyme activities in millet by rationing molybdenum and nitrogen.","authors":"Yuan Zhao, Guoliang Wang, Min Liu, HongTao Xue, PeiYue Zhao, BaiShu Han, HuiPing Fan, Rui Wang, LiXia Wang, ErHu Guo, AiYing Zhang","doi":"10.3389/fpls.2024.1524347","DOIUrl":"10.3389/fpls.2024.1524347","url":null,"abstract":"<p><p>The application of appropriate nitrogen and molybdenum fertilizer can improve the growth and development of plants, increase photosynthetic efficiency, regulate active oxygen metabolism <i>in vivo</i>, maintain the oxidation balance required for normal cell growth, enhance the activity of crop antioxidant enzymes and dry matter accumulation, so as to increase crop yield. In order to investigate the effect mechanism of nitrogen fertilizer combined with foliar molybdenum fertilizer on millet yield and antioxidant enzyme activity, two nitrogen application gradients (N<sub>0</sub> (0 kg/hm2) and N<sub>1</sub> (75 kg/hm2) were set with millet variety Changnong 47 as material. Leaf molybdenum fertilizer Mo<sub>0</sub> (0 %), Mo<sub>1</sub> (0.1 %), Mo<sub>2</sub> (0.2 %), Mo<sub>3</sub> (0.3 %) and Mo<sub>4</sub> (0.4 %) were sprayed at the joining stage. Photosynthetic parameters, chlorophyll content, antioxidant enzyme activity, dry matter accumulation and yield at the complete ripening stage were measured. After the analysis of significant difference, the results showed that the combined application of molybdenum nitrogen significantly increased the yield of millet, and the maximum yield under the Mo3 treatment was 5869.04 kg/hm<sub>2</sub> under the N1 condition, which was 13% higher than that under the no fertilization treatment. The total dry matter accumulation was 36.96 g/ plant, which was 31% higher than that without fertilization. The net photosynthetic rate (Pn) and stomatal conductivity (gs) increased first and then decreased with the increase of molybdenum fertilizer concentration gradient, and reached the maximum values under N<sub>1</sub>Mo<sub>3</sub> condition, which were 24.77 μmol•m<sub>-2</sub>•s<sub>-1</sub> and 391.33 mol•m<sub>-2</sub>•s<sub>-1</sub>, respectively. Application of molybdenum fertilizer can improve the activities of superoxide dismutase (SOD), peroxidase (POD) and catalase (CAT) in the test samples. In conclusion, under N<sub>1</sub> condition, Mo<sub>3</sub> (0.3%) treatment can effectively improve millet yield, photosynthetic characteristics and antioxidant enzyme activity. The results of this study provided theoretical basis and data support for the application of nitrogen and molybdenum fertilizer in millet production.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1524347"},"PeriodicalIF":4.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11795666/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143255414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Construction and evaluation of <i>Brassica rapa</i> orphan genes overexpression library.","authors":"Mingliang Jiang, Zongxiang Zhan, Xiaonan Li, Zhongyun Piao","doi":"10.3389/fpls.2025.1532449","DOIUrl":"10.3389/fpls.2025.1532449","url":null,"abstract":"<p><p>Orphan genes (<i>OGs</i>) are crucial for species-specific characteristics and stress responses and are restricted to a specific taxon. However, their functions within particular species are poorly understood. Previous research identified <i>OGs</i> in <i>Brassica rapa</i> (<i>BrOGs</i>). In this study, the <i>BrOGs</i> overexpression (BrOGsOE) library in <i>Arabidopsis thaliana</i> was constructed. Approximately 128 unknown functional <i>BrOGs</i> were selected from Chinese cabbage and were overexpressed. The analysis focused on the phenotypes of leaf morphology and flowering time against phenotypic differences between Chinese cabbage and <i>Arabidopsis</i>. Interestingly, 72.66% of the transgenic lines showed distinctive phenotypic changes. Chinese cabbage-specific features, including curved, hairy, upward or downward-curving leaves, serrated margins, and multiple leaves, were observed in the BrOGsOE lines. The <i>BrOGs</i> overexpression library was associated with numerous variations in flowering time, particularly delayed flowering. This suggested that the delayed flowering time caused by <i>BrOGs</i> may be associated with resistance to bolting seem in Chinese cabbage. Furthermore, the results of stress treatment of 24 BrOGsOE lines with no apparent significant phenotypes suggested that a number of <i>BrOGs</i> have both general and specific functions against environmental and pathogenic stress. The findings of this study provide a comprehensive overview of the roles of <i>BrOGs</i>, emphasizing their significance as a resource for identifying positive genes associated with species-specific characteristics and stress responses and offering a solid foundation for the functional analysis of <i>BrOGs</i>.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1532449"},"PeriodicalIF":4.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11794797/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143255416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Frontiers in Plant SciencePub Date : 2025-01-22eCollection Date: 2024-01-01DOI: 10.3389/fpls.2024.1476754
Haoqiang Yu, Hong Lv, Fengzhong Lu, Qingqing Yang, Huaming Duan, Wanchen Li, Fengling Fu
{"title":"Expression evaluation of exogenous and endogenous alcohol dehydrogenase genes in transgenic <i>Arabidopsi</i>s.","authors":"Haoqiang Yu, Hong Lv, Fengzhong Lu, Qingqing Yang, Huaming Duan, Wanchen Li, Fengling Fu","doi":"10.3389/fpls.2024.1476754","DOIUrl":"10.3389/fpls.2024.1476754","url":null,"abstract":"<p><p>A lot of endogenous genes, as well as genes from related species, are transformed back into crops for overexpression to improve their corresponding traits. However, almost all of these transgenic events remain at the testing stage. Most of the singular transgenic events of crops approved for commercial release are developed by the transformation and heterologous expression of exogenous genes from distant species. To detect the differences in expression, protein accumulation, and enzyme activity between transformed exogenous and endogenous genes, the coding sequences (CDSs) of the alcohol dehydrogenase (ADH) genes were cloned from dicotyledonous <i>Arabidopsis</i>, monocotyledonous maize, and prokaryotic <i>Escherichia coli</i>, constructed into expression vector pBI121-cMycNY, and used to transform wild-type <i>Arabidopsis</i>, respectively. Three homozygous T<sub>3</sub> lines with a single integration site were screened for each of the three transformed genes by antibiotic screening, polymerase chain reaction (PCR) identification, and genomic DNA resequencing. Real-time quantitative PCR (RT-qPCR) analysis showed that the relative expression levels of the transformed exogenous <i>ZmADH</i> and <i>EcADH</i> genes were ten or tens of times higher than that of the transformed endogenous <i>AtADH</i> gene. After confirming the encoded proteins of these transformed genes by Western blotting, enzyme-linked immunosorbent assay (ELISA) showed that the accumulation levels of the proteins encoded by the transformed genes <i>ZmADH</i> and <i>EcADH</i> were significantly higher than that encoded by the transformed endogenous gene <i>AtADH</i>. Enzyme reaction assay showed that the ADH activities of the T<sub>3</sub> lines transformed by the exogenous genes <i>ZmADH</i> and <i>EcADH</i> were also significantly higher than that transformed by the endogenous gene <i>AtADH</i> as well as the wild-type control. These results indicated that exogenous genes were more conducive to transgenic improvement of crops.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1476754"},"PeriodicalIF":4.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11794282/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143254913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Frontiers in Plant SciencePub Date : 2025-01-22eCollection Date: 2024-01-01DOI: 10.3389/fpls.2024.1518294
Jun Li, Kaixuan Wu, Meiqi Zhang, Hengxu Chen, Hengyi Lin, Yuju Mai, Linlin Shi
{"title":"YOLOv8s-Longan: a lightweight detection method for the longan fruit-picking UAV.","authors":"Jun Li, Kaixuan Wu, Meiqi Zhang, Hengxu Chen, Hengyi Lin, Yuju Mai, Linlin Shi","doi":"10.3389/fpls.2024.1518294","DOIUrl":"10.3389/fpls.2024.1518294","url":null,"abstract":"<p><strong>Introduction: </strong>Due to the limited computing power and fast flight speed of the picking of unmanned aerial vehicles (UAVs), it is important to design a quick and accurate detecting algorithm to obtain the fruit position.</p><p><strong>Methods: </strong>This paper proposes a lightweight deep learning algorithm, named YOLOv8s-Longan, to improve the detection accuracy and reduce the number of model parameters for fruitpicking UAVs. To make the network lightweight and improve its generalization performance, the Average and Max pooling attention (AMA) attention module is designed and integrated into the DenseAMA and C2f-Faster-AMA modules on the proposed backbone network. To improve the detection accuracy, a crossstage local network structure VOVGSCSPC module is designed, which can help the model better understand the information of the image through multiscale feature fusion and improve the perception and expression ability of the model. Meanwhile, the novel Inner-SIoU loss function is proposed as the loss function of the target bounding box.</p><p><strong>Results and discussion: </strong>The experimental results show that the proposed algorithm has good detection ability for densely distributed and mutually occluded longan string fruit under complex backgrounds with a mAP@0.5 of 84.3%. Compared with other YOLOv8 models, the improved model of mAP@0.5 improves by 3.9% and reduces the number of parameters by 20.3%. It satisfies the high accuracy and fast detection requirements for fruit detection in fruit-picking UAV scenarios.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1518294"},"PeriodicalIF":4.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11794187/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143255415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Frontiers in Plant SciencePub Date : 2025-01-22eCollection Date: 2025-01-01DOI: 10.3389/fpls.2025.1489244
Avinash Shrestha, Christian J Stephens, Rosalyn B Angeles-Shim
{"title":"Taming wild genomes: perspectives on mechanisms governing differential introgression in exotic rice germplasm and their applications in breeding.","authors":"Avinash Shrestha, Christian J Stephens, Rosalyn B Angeles-Shim","doi":"10.3389/fpls.2025.1489244","DOIUrl":"10.3389/fpls.2025.1489244","url":null,"abstract":"<p><p>Wide hybridization is an important plant breeding strategy that can be used to expand the available genetic variation in present-day crops towards breeding for enhanced agronomic performance. The primary challenge in wide hybridization is the presence of reproductive barriers and genetic incompatibilities that limit the transfer of desirable wild or distant alleles in the genetic background of cultivated plant species. Here we provide perspectives on the possible role of hybrid sterility and gametocidal genes on the observed preferential introgression in exotic germplasm of rice. We argue that while these aberrant introgression and segregation behavior of wild or distant chromosomes presents significant barriers in exploiting ancestral germplasm in breeding, the same mechanisms can also be exploited to enhance the transfer of wild alleles in a cultivated genetic background. Understanding the genetic basis of preferential introgression and segregation in wide hybrids will have serious implications in our ability to capture ancestral genetic variation that can add significant agronomic value to staple crops like rice.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1489244"},"PeriodicalIF":4.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11794820/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143255418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An improved ShuffleNetV2 method based on ensemble self-distillation for tomato leaf diseases recognition.","authors":"Shuiping Ni, Yue Jia, Mingfu Zhu, Yizhe Zhang, Wendi Wang, Shangxin Liu, Yawei Chen","doi":"10.3389/fpls.2024.1521008","DOIUrl":"10.3389/fpls.2024.1521008","url":null,"abstract":"<p><strong>Introduction: </strong>Timely and accurate recognition of tomato diseases is crucial for improving tomato yield. While large deep learning models can achieve high-precision disease recognition, these models often have a large number of parameters, making them difficult to deploy on edge devices. To address this issue, this study proposes an ensemble self-distillation method and applies it to the lightweight model ShuffleNetV2.</p><p><strong>Methods: </strong>Specifically, based on the architecture of ShuffleNetV2, multiple shallow models at different depths are constructed to establish a distillation framework. Based on the fused feature map that integrates the intermediate feature maps of ShuffleNetV2 and shallow models, a depthwise separable convolution layer is introduced to further extract more effective feature information. This method ensures that the intermediate features from each model are fully preserved to the ensemble model, thereby improving the overall performance of the ensemble model. The ensemble model, acting as the teacher, dynamically transfers knowledge to ShuffleNetV2 and the shallow models during training, significantly enhancing the performance of ShuffleNetV2 without changing the original structure.</p><p><strong>Results: </strong>Experimental results show that the optimized ShuffleNetV2 achieves an accuracy of 95.08%, precision of 94.58%, recall of 94.55%, and an F1 score of 94.54% on the test set, surpassing large models such as VGG16 and ResNet18. Among lightweight models, it has the smallest parameter count and the highest recognition accuracy.</p><p><strong>Discussion: </strong>The results demonstrate that the optimized ShuffleNetV2 is more suitable for deployment on edge devices for real-time tomato disease detection. Additionally, multiple shallow models achieve varying degrees of compression for ShuffleNetV2, providing flexibility for model deployment.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1521008"},"PeriodicalIF":4.1,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11790667/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143188931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Frontiers in Plant SciencePub Date : 2025-01-21eCollection Date: 2024-01-01DOI: 10.3389/fpls.2024.1518369
Danilo M Rocha, Ulla Neumann, Fernanda M Nogueira, Georgios Tsipas, André L L Vanzela, André Marques
{"title":"Cryoimmobilized anther analysis reveals new ultrastructural insights into <i>Rhynchospora</i> (Cyperaceae) asymmetrical microsporogenesis.","authors":"Danilo M Rocha, Ulla Neumann, Fernanda M Nogueira, Georgios Tsipas, André L L Vanzela, André Marques","doi":"10.3389/fpls.2024.1518369","DOIUrl":"10.3389/fpls.2024.1518369","url":null,"abstract":"<p><strong>Introduction: </strong>The Cyperaceae family is distinguished by holocentric chromosomes and a distinctive microsporogenesis process, which includes inverted meiosis, asymmetric tetrad formation, selective cell death, and the formation of pseudomonad pollen. Despite significant advances, the ultrastructural details of these processes remain poorly understood.</p><p><strong>Methods: </strong>This study provides a detailed analysis of microsporogenesis in <i>Rhynchospora pubera</i> using high-pressure freezing, freeze substitution, and transmission electron microscopy, significantly enhancing ultrastructural resolution.</p><p><strong>Results and discussion: </strong>Our findings reveal that intracellular organization differs from model species <i>Arabidopsis thaliana</i> and drives nuclear selection, with endoplasmic reticulum vesicles organizing meiotic spindles. Microtubules attach to centromeres located deep within holocentric chromosomes, while extensive cytoplasmic connections facilitate material exchange until callose deposition encloses meiocytes. Lipid distribution contributes to cell asymmetry, resulting in the characteristic asymmetric tetrads. Following meiosis, cytoskeletal elements coordinate nuclear migration and cell plate formation. Pseudomonads exhibit reconfigurations in the endomembrane system, particularly involving the endoplasmic reticulum, which supports functional cell differentiation. Complementary histochemical analyses corroborate these findings, providing insights into the cellular processes governing <i>Rhynchospora</i> microsporogenesis. These findings contribute to a deeper understanding of the developmental processes of Cyperaceae pollen, thereby facilitating future investigations of the underlying molecular mechanisms.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1518369"},"PeriodicalIF":4.1,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11790663/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143188959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Genome-wide identification and expression analysis of bHLH gene family revealed their potential roles in abiotic stress response, anthocyanin biosynthesis and trichome formation in <i>Glycyrrhiza uralensis</i>.","authors":"Guohua Ding, Yanping Shi, Kerui Xie, Hongbin Li, Guanghui Xiao","doi":"10.3389/fpls.2024.1485757","DOIUrl":"10.3389/fpls.2024.1485757","url":null,"abstract":"<p><strong>Introduction: </strong>Licorice stands out as an exceptional medicinal resource with a long history of application, attributed to its substantial pharmacological potential. The basic helix-loop-helix (bHLH) transcription factors (TFs) gene family, being the second-largest in plants, is vital for plant development and adapting to environmental shifts. Despite this, the comprehensive characteristics of licorice <i>bHLH</i> gene family are not well-documented.</p><p><strong>Results: </strong>In this study, a detailed and thorough genome-wide identification and expression analysis of <i>Glycyrrhiza uralensis bHLH</i> gene family was carried out, resulting in the identification of 139 licorice <i>bHLH</i> members. Our duplication analysis highlighted the significant contribution of segmental duplications to the expansion of <i>G. uralensis bHLH</i> genes, with <i>GubHLH</i> genes experiencing negative selection throughout evolution. It was discovered that GubHLH64 and GubHLH38 could be importantly linked to the licorice trichome initiation and anthocyanin biosynthesis and GubHLH64 was also involved in the abiotic stress response. Additionally, certain subfamily III (d+e) GubHLH members could be implicated in the licorice drought response. GubHLH108, GubHLH109, and GubHLH116 were suggested to form a tightly related cluster, initiating transcriptional responses via JA signaling pathway.</p><p><strong>Discussion: </strong>In summary, our findings furnish a foundational understanding for future investigations of <i>GubHLH</i> gene functions and regulation mechanisms, shedding light on the potential applications of licorice in medicine and agriculture.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1485757"},"PeriodicalIF":4.1,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11790457/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143188904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Chrysanthemum classification method integrating deep visual features from both the front and back sides.","authors":"Yifan Chen, Xichen Yang, Hui Yan, Jia Liu, Jian Jiang, Zhongyuan Mao, Tianshu Wang","doi":"10.3389/fpls.2024.1463113","DOIUrl":"10.3389/fpls.2024.1463113","url":null,"abstract":"<p><strong>Introducion: </strong>Chrysanthemum morifolium Ramat (hereinafter referred to as Chrysanthemum) is one of the most beloved and economically valuable Chinese herbal crops, which contains abundant medicinal ingredients and wide application prospects. Therefore, identifying the classification and origin of Chrysanthemum is important for producers, consumers, and market regulators. The existing Chrysanthemum classification methods mostly rely on visual subjective identification, are time-consuming, and always need high equipment costs.</p><p><strong>Methods: </strong>A novel method is proposed to accurately identify the Chrysanthemum classification in a swift, non-invasive, and non-contact way. The proposed method is based on the fusion of deep visual features of both the front and back sides. Firstly, the different Chrysanthemums images are collected and labeled with origins and classifications. Secondly, the background area with less available information is removed by image preprocessing. Thirdly, a two-stream feature extraction network is designed with two inputs which are the preprocessed front and back Chrysanthemum images. Meanwhile, the incorporation of single-stream residual connections and cross-stream residual connections is employed to extend the receptive field of the network and fully fusion the features from both the front and back sides.</p><p><strong>Results: </strong>Experimental results demonstrate that the proposed method achieves an accuracy of 93.8%, outperforming existing methods and exhibiting superior stability.</p><p><strong>Discussion: </strong>The proposed method provides an effective and dependable solution for identifying Chrysanthemum classification and origin while offering practical benefits for quality assurance in production, consumer markets, and regulatory processes. Code and data are available at https://github.com/dart-into/CCMIFB.</p>","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"15 ","pages":"1463113"},"PeriodicalIF":4.1,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11790631/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143188950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}