Image Recognition Method Based on an Improved Convolutional Neural Network to Detect Impurities in Wheat
文献类型： 外文期刊
作者： Shen, Yin 1 ; Yin, Yanxin 2 ; Zhao, Chunjiang 1 ; Li, Bin 2 ; Wang, Jun 4 ; Li, Guanglin 1 ; Zhang, Ziqiang 5 ;
作者机构： 1.Southwest Univ, Coll Engn & Technol, Chongqing 400715, Peoples R China
2.Natl Res Ctr Intelligent Equipment Agr, Beijing 100097, Peoples R China
3.Beijing Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China
4.Sichuan Univ, Sch Elect & Informat Engn, Chengdu 610064, Sichuan, Peoples R China
5.Capital Normal Univ, Informat Engn Coll, Beijing 100048, Peoples R China
关键词： Impurities; Image recognition; Training; Agricultural machinery; Convolutional neural networks; Classification algorithms; Licenses; Wheat images; impurity recognition; convolution neural network; WheNet network
期刊名称：IEEE ACCESS （ 影响因子：3.367； 五年影响因子：3.671 ）
ISSN： 2169-3536
年卷期： 2019 年 7 卷
页码：
收录情况： SCI
摘要： Impurities in wheat seriously affect wheat quality and food security. They are mainly produced during the operational process of combine harvesters. To solve the recognition and classification problems associated with impurities in wheat, a recognition method using an improved convolutional neural network is proposed in this article. A labeled dataset of normal wheat and five impurities is constructed, using which the Wiener filtering algorithm and the multi-scale Retinex enhancement algorithm are employed for image preprocessing. Based on network research using Inceptionv3, improvement and optimization are undertaken before designing the WheNet convolutional neural network, which is intended for automatic recognition of wheat images. Under the same conditions, comparative experiments using the WheNet, ResNet101 and Inceptionv3 networks are conducted. Indexes such as receiver operating characteristic, area under curve (AUC), and recall rate are adopted to evaluate the experimental outcomes. Experimental results indicate that the WheNet network achieved the most efficient results. It also shows a shorter training time, and its recognition accuracies for Top1 and Top5 of the test set are 98.59 and 99.98, respectively. The mean values of both the AUC and recall rate of the network on the recognition of various images of impurities are higher than those of the ResNet101 and Inceptionv3 networks. Consequently, the WheNet network can be a useful tool in recognizing impurities in wheat. Furthermore, this method can be used to detect impurities in other fields.
- 相关文献
作者其他论文 更多>>
-
Recognition of maize seedling under weed disturbance using improved YOLOv5 algorithm
作者：Tang, Boyi;Zhao, Chunjiang;Tang, Boyi;Zhou, Jingping;Pan, Yuchun;Qu, Xuzhou;Cui, Yanglin;Liu, Chang;Li, Xuguang;Zhao, Chunjiang;Gu, Xiaohe;Li, Xuguang
关键词：Object detection; Maize seedlings; UAV RGB images; YOLOv5; Attention mechanism
-
Boosting Cost-Efficiency in Robotics: A Distributed Computing Approach for Harvesting Robots
作者：Xie, Feng;Xie, Feng;Li, Tao;Feng, Qingchun;Li, Tao;Feng, Qingchun;Chen, Liping;Zhao, Chunjiang;Zhao, Hui
关键词：5G network; computation allocation; edge computing; harvesting robot; visual system
-
Genotyping Identification of Maize Based on Three-Dimensional Structural Phenotyping and Gaussian Fuzzy Clustering
作者：Xu, Bo;Zhao, Chunjiang;Xu, Bo;Zhao, Chunjiang;Yang, Guijun;Zhang, Yuan;Liu, Changbin;Feng, Haikuan;Yang, Xiaodong;Yang, Hao;Xu, Bo;Zhao, Chunjiang;Yang, Guijun;Zhang, Yuan;Liu, Changbin;Feng, Haikuan;Yang, Xiaodong;Yang, Hao
关键词：tassel; 3D phenotyping; TreeQSM; genotyping; clustering
-
Rapid and highly sensitive detection of trace chromium and copper in tea infusion using laser-induced breakdown spectroscopy combined with electrospinning technology
作者：He, Panyu;Fu, Xinglan;Wang, Chenghao;Gou, Yujiang;An, Ting;Li, Guanglin;Cao, Fengjing;Tian, Hongwu;Ma, Shixiang;Liang, Yiyi
关键词：Laser-induced breakdown spectroscopy (LIBS); Electrospinning (ES); Tea infusion; Nanoparticles(NPs); Electrospun nanofiber membranes (ENM); Heavy metals detection
-
High-throughput phenotyping techniques for forage: Status, bottleneck, and challenges
作者：Cheng, Tao;Zhang, Dongyan;Cheng, Tao;Wang, Zhaoming;Zhang, Dongyan;Zhang, Gan;Yuan, Feng;Liu, Yaling;Wang, Tianyi;Ren, Weibo;Zhao, Chunjiang
关键词：Forage; High-throughput phenotyping; Precision identification; Sensors; Artificial intelligence; Efficient breeding
-
A New System for Evaluating the Ability to Release Negative Ions-Taking Urban Forests as an Example
作者：Li, Shaoning;Li, Tingting;Yu, Di;Zhao, Na;Xu, Xiaotian;Li, Bin;Lu, Shaowei;Li, Shaoning;Zhao, Na;Xu, Xiaotian;Li, Bin;Lu, Shaowei;Li, Shaoning;Li, Tingting;Yu, Di;Lu, Shaowei
关键词：negative air ions; release ability; evaluation system; meteorological factors; forest park
-
EasyMetagenome: A user-friendly and flexible pipeline for shotgun metagenomic analysis in microbiome research
作者：Bai, Defeng;Xun, Jiani;Ma, Chuang;Luo, Hao;Yang, Haifei;Hou, Huiyu;Lv, Hujie;Wan, Xiulin;Wang, Yao;Yousuf, Salsabeel;Zeng, Meiyin;Zhang, Tianyuan;Gao, Yunyun;Liu, Yong-Xin;Chen, Tong;Ma, Chuang;Yang, Haifei;Cao, Chen;Cao, Xiaofeng;Cui, Jianzhou;Deng, Yuan-Ping;Deng, Zhaochao;Yu, Hao;Zhang, Chunfang;Dong, Wenxin;Dong, Wenxue;Du, Juan;Fang, Qunkai;Fang, Wei;Fang, Yue;Luan, Yaning;Fu, Fangtian;Fu, Min;Fu, Yi-Tian;Gao, He;Ge, Jingping;Guo, Yuhao;Gong, Qinglong;Lou, Wenbo;Gu, Lunda;Yang, Li;Guo, Peng;Hai, Tang;Liu, Hao;He, Jieqiang;He, Zi-Yang;Huang, Can;Ji, Shuai;Jiang, ChangHai;Jiang, Gui-Lai;Jiang, Lingjuan;Jin, Ling N.;Li, Changchao;Kan, Yuhe;Kang, Da;Kou, Jin;Lam, Ka-Lung;Li, Chong;Li, Fuyi;Li, Liwei;Li, Miao;Li, Xin;Li, Ye;Li, Zheng-Tao;Zhu, Chengshuai;Liang, Jing;Mo, Jiayuan;Lin, Yongxin;Liu, Changzhen;Liu, Danni;Zhang, Jing;Chen, Shifu;Liu, Fengqin;Liu, Jia;Liu, Tianrui;Liu, Tingting;Wang, Xinlong;Liu, Xinyuan;Luo, Yuanyuan;Liu, Yaqun;Liu, Bangyan;Liu, Minghao;Lv, Hujie;Ma, Tengfei;Mai, Zongjiong;Niu, Dongze;Pan, Zhuo;Qi, Heyuan;Shi, Zhanyao;Song, Chunjiao;Sun, Fuxiang;Sun, Yan;Tian, Sihui;Wang, Guoliang;Wang, Hongyang;Wang, Hongyu;Wang, Huanhuan;Wang, Jing;Wang, Jun;Wang, Kang;Wang, Leli;Yao, Xiaofang;Wang, Shao-kun;Xiao, Zufei;Xing, Huichun;Xu, Yifan;Yang, Song;Yan, Shu-yan;Zhang, Yi-Bo;Yang, Yuanming;Lei, Yu;Yuan, Zhengrong;Zhang, Chunge;Zhang, Huimin;Zhang, Na;Zhang, Yupeng;Zhang, Zheng;Zhou, Mingda;Zhou, Yuanping;Zhu, Zhihao;Zhu, Lin;Zhu, Yue;Zou, Hongqin;Zuo, Anna;Dong, Wenxuan;Wen, Tao;Chen, Shifu;Chen, Shifu;Li, Guoliang
关键词：metagenome; microbiome; microbiota; pipeline; visualization
