Rapid and non-destructive classification of rice seeds with different flavors: an approach based on HPFasterNet
文献类型： 外文期刊
作者： Yu, Helong 1 ; Chen, Zhenyang 1 ; Song, Shaozhong 1 ; Qi, Chunyan 4 ; Liu, Junling 3 ; Yang, Chenglin 2 ;
作者机构： 1.Jilin Agr Univ, Smart Agr Res Inst, Changchun, Peoples R China
2.Jilin Agr Univ, Coll Informat Technol, Changchun, Peoples R China
3.Jilin Engn Normal Univ, Sch Data Sci & Artificial Intelligence, Changchun, Peoples R China
4.Jilin Acad Agr Sci, Rice Res Inst, Changchun, Peoples R China
关键词： rice seed classification; japonica rice; deep learning; different flavored rice; lightweight network
期刊名称：FRONTIERS IN PLANT SCIENCE （ 影响因子：4.8； 五年影响因子：5.7 ）
ISSN： 1664-462X
年卷期： 2025 年 15 卷
页码：
收录情况： SCI
摘要： Rice is an important part of the food supply, its different varieties in terms of quality, flavor, nutritional value, and other aspects of the differences, directly affect the subsequent yield and economic benefits. However, traditional rice identification methods are time-consuming, inefficient, and prone to damage. For this reason, this study proposes a deep learning-based method to classify and identify rice with different flavors in a fast and non-destructive way. In this experiment, 19 categories of japonica rice seeds were selected, and a total of 36735 images were finally obtained. The lightweight network High Precision FasterNet (HPFasterNet) proposed in this study combines the Ghost bottleneck and FasterNet_T0 and introduces group convolution to compare the model performance. The results show that HPFasterNet has the highest classification accuracy of 92%, which is 5.22% better than the original model FasterNet_T0, and the number of parameters and computation is significantly reduced compared to the original model, which is more suitable for resource-limited environments. Comparison with three classical models and three lightweight models shows that HPFasterNet exhibits a more comprehensive and integrated performance. Meanwhile, in this study, HPFasterNet was used to test rice with different flavors, and the accuracy reached 98.98%. The experimental results show that the network model proposed in this study can be used to provide auxiliary experiments for rice breeding and can also be applied to consumer and food industries.
- 相关文献
作者其他论文 更多>>
-
Multienzyme cascade for synthesis of hydroxytyrosol via engineered Escherichia coli
作者：Xiong, Tianzhen;Li, Xinmeng;Yue, Huidie;Liu, Junling;Bai, Dingyuan;Li, Wei;Fan, Guangyan;Xiong, Tianzhen;Li, Xinmeng;Yue, Huidie;Liu, Junling;Bai, Dingyuan;Li, Wei;Fan, Guangyan;Xiong, Tianzhen;Liu, Wei;Xiong, Tianzhen
关键词：Hydroxytyrosol;
Escherichia coli ; Cascade reaction; Whole cell biotransformation -
A sorghum seed variety identification method based on image-hyperspectral fusion and an improved deep residual convolutional network
作者：Yang, Xu;Chen, Yihan;Song, Shaozhong;Zhang, Zhimin
关键词：artificial intelligence; sorghum seed; variety identification; multi-modal fusion; ResNet models
-
Classification of Rice Seeds Grown in Different Geographical Environments: An Approach Based on Improved Residual Networks
作者：Yu, Helong;Yang, Chenglin;Yu, Helong;Chen, Zhenyang;Song, Shaozhong;Chen, Mojun
关键词：rice region classification; residual network; rice soil; deep learning
-
Crop Disease Detection against Complex Background Based on Improved Atrous Spatial Pyramid Pooling
作者：Ma, Wei;Ma, Dianrong;Ma, Wei;Fang, Wenbo;Guan, Fachun;Zhang, Zhengchao;Wang, Chao;Yu, Helong;Fang, Wenbo;Guo, Yonggang;Zhang, Zhengchao
关键词：disease; dual attention; dilated convolution; machine learning
-
Combined laser-induced breakdown spectroscopy and hyperspectral imaging with machine learning for the classification and identification of rice geographical origin
作者：Liu, Yuanyuan;Gao, Xun;Fu, Shaoyan;Dou, Yinping;Lin, Jingquan;Zhao, Shangyong;Song, Chao;Qi, Chunyan
关键词：
-
Identification of wormholes in soybean leaves based on multi-feature structure and attention mechanism
作者：Fang, Wenbo;Guo, Yonggang;Su, Libin;Zhang, Zhengchao;Fang, Wenbo;Guan, Fachun;Cui, Yanru;Xie, Jiao;Yu, Helong;Bi, Chunguang
关键词：Wormhole; attention; YOLO-v5s; Machine learning; improved method
