检索结果-南通市图书馆

weed classification Using Particle Swarm Optimization and Deep Learning Models

Computer Systems Science & Engineering 2023年第1期44卷 913-927页

作者： M.Manikandakumar P.Karthikeyan Department of Computer Science and Engineering Thiagarajar College of EngineeringTamil NaduIndia Department of Information Technology Thiagarajar College of EngineeringTamil NaduIndia

weed is a plant that grows along with nearly allfield crops,including rice,wheat,cotton,millets and sugar cane,affecting crop yield and *** and accurate identification of all types of weeds is a challenging task for farmers in earlier stage of crop growth because of *** address this issue,an efficient weed classification model is proposed with the Deep Convolutional Neural Network(CNN)that implements automatic feature extraction and performs complex feature learning for image *** this work,weed images were trained using the proposed CNN model with evolutionary computing approach to classify the weeds based on the two publicly available weed *** Tamil Nadu Agricultural University(TNAU)dataset used as afirst dataset that consists of 40 classes of weed images and the other dataset is from Indian Council of Agriculture Research–Directorate of weed Research(ICAR-DWR)which contains 50 classes of weed *** effective Particle Swarm Optimization(PSO)technique is applied in the proposed CNN to automa-tically evolve and improve its classification *** proposed model was evaluated and compared with pre-trained transfer learning models such as GoogLeNet,AlexNet,Residual neural Network(ResNet)and Visual Geometry Group Network(VGGNet)for weed *** work shows that the performance of the PSO assisted proposed CNN model is significantly improved the success rate by 98.58%for TNAU and 97.79%for ICAR-DWR weed datasets.

关键词： Deep learning convolutional neural network weed classification transfer learning particle swarm optimization evolutionary computing Algorithm 1:Metrics Evaluation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Review of deep learning-based weed identification in crop fields

引用

International Journal of Agricultural and Biological Engineering 2023年第4期16卷 1-10页

作者： Wenze Hu Samuel Oliver Wane Junke Zhu Dongsheng Li Qing Zhang Xiaoting Bie Yubin Lan School of Agricultural Engineering and Food Science Shandong University of TechnologyZibo 255000ShandongChina Department of Agricultural Engineering Harper Adams UniversityNewport TF108NBShropshireUK School of Computer Science and Technology Shandong University of TechnologyZibo 255000ShandongChina Academy of Ecological Unmanned Farm Zibo 255000ShandongChina

Automatic weed identification and detection are crucial for precision weeding *** recent years,deep learning(DL)has gained widespread attention for its potential in crop weed *** paper provides a review of the current research status and development trends of weed identification in crop fields based on *** an analysis of relevant literature from both within and outside of China,the author summarizes the development history,research progress,and identification and detection methods of DL-based weed identification *** is placed on data sources and DL models applied to different technical ***,the paper discusses the challenges of time-consuming and laborious dataset preparation,poor generality,unbalanced data categories,and low accuracy of field identification in DL for weed *** solutions are proposed to provide a reference for future research directions in weed identification.

关键词： deep learning weed detection weed classification cation image segmentation Convolutional Neural Network image processing

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A study on deep learning algorithm performance on weed and crop species identification under different image background

引用

Artificial Intelligence in Agriculture 2022年第1期6卷 242-256页

作者： Sunil G C Cengiz Koparan Mohammed Raju Ahmed Yu Zhang Kirk Howatt Xin Sun Department of Agricultural and Biosystems Engineering North Dakota State UniversityFargoND 58108USA Department of Plant Sciences North Dakota State UniversityPO Box 6050FargoND 58108-6050USA

weed identification is fundamental toward developing a deep learning-based weed control *** learning algorithms assist to build a weed detection model by using weed and crop *** dynamic environmental conditions such as ambient lighting,moving cameras,or varying image backgrounds could affect the performance of deep learning *** are limited studies on how the different image backgrounds would impact the deep learning algorithms for weed *** objective of this research was to test deep learning weed identification model performance in images with potting mix(non-uniform)and black pebbled(uniform)backgrounds *** weed and crop images were acquired by four canon digital cameras in the greenhouse with both uniform and non-uniform background conditions.A Convolutional Neural Network(CNN),Visual Group Geometry(VGG16),and Residual Network(ResNet50)deep learning architectures were used to build weed classification *** model built from uniform background images was tested on images with a non-uniform background,as well as model built from non-uniform background images was tested on images with uniform *** showed that the VGG16 and ResNet50 models built from non-uniform background images were evaluated on the uniform background,achieving models'performance with an average f1-score of 82.75%and 75%,***,the VGG16 and ResNet50 models built from uniform background images were evaluated on the non-uniform background images,achieving models'performance with an average f1-score of 77.5%and 68.4%*** the VGG16 and ResNet50 models'performances were im-proved with average f1-score values between 92%and 99%when both uniform and non-uniform background images were used to build the *** appears that the model performances are reduced when they are tested with images that have different object background than the ones used for building the model.

关键词： Computer vision Deep learning Image background Neural network weed classification

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

weed Species Composition in Paddy Field of Usur Town,Bade Local Government,Yobe State,Nigeria

引用

Journal of Botanical Research 2023年第2期5卷 29-48页

作者： Mohammed Alhaji Bello Halima Mohammed Abba Umar Mohammed Department of Biological Science Education School of SciencesUmar Suleiman College of Education GashuaP.M.B.02Yobe StateNigeria Department of Botany Faculty of SciencesGombe State UniversityGombe State760211Nigeria Department of Agricultural Science Education School of Vocational EducationUmar Suleiman College of Education GashuaP.M.B.02Yobe StateNigeria

Farmers are eager to know the various types of weeds in paddy *** will help in choosing the best weed management practice for effective weed control as well as reducing rice yield *** objectives of the study are to identify the weeds species affecting the rice field,to assess the composition of weeds species,to classify the weed species into different families,genera,species,common names,Hausa names,lifecycles,life forms,native/exotic species,propagation and uses,and to determine the dominant weed *** vegetation surveys were *** observed were photographed,and prepared as herbarium *** key manuals and checklists were utilized for weed identification and later organized using the Angiosperm Phylogeny Group(APG)classification system.A total number of 72 plants species distributed within 16 families and 50 genera were *** annuals(66.67%)were the dominant weed followed by perennials(33.33%)while biennials were the *** broad leaves were the dominant weed(44.61%)identified followed by Poaceae(27.7%)and Sedges(11.11%).Results obtained from this study could be useful in choosing the best management practice and in making a decision on the choice of herbicides and directing research towards improved weed control measures.

关键词： Rice Dominant weeds Exotic species Native species weed classification

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：