Journal of Jilin University(Engineering and Technology Edition) ›› 2018, Vol. 48 ›› Issue (6): 1873-1878.doi: 10.13229/j.cnki.jdxbgxb20180497

Previous Articles     Next Articles

Agricultural surface multiple feature decision fusion disease judgment algorithm based on machine vision

LIU En-ze(),WU Wen-fu()   

  1. College of Biological and Agricultural Engineering, Jilin University, Changchun 130022,China
  • Received:2018-05-22 Online:2018-11-20 Published:2018-12-11

Abstract:

For the judgment of the lesions of large-scale planted crops, this paper uses machine vision technology to propose an agricultural disease judgment algorithm based on surface multiple feature decision fusion. First the images of multiple agricultural leaves are collected that different surface feature extraction algorithms are applied to each leaf. Second, the feature weights are set and different features are combined to determine the likelihood of lesions in the leaf. Finally, the method of majority voting decision is used to judge the lesions in the region of each leaf. Compare with the artificial judgment method, this algorithm reduces the workload and can provide effective early warning of crop diseases.

Key words: computer application, machine vision, agricultural disease judgment, surface multiple feature, feature weight, majority voting decision

CLC Number: 

  • TP391

Fig.1

Disease judgment algorithm structure diagram"

Fig.2

Leaf image"

Fig.3

Neural network structure"

Fig.4

Leaf image of various lesions"

Table 1

Experimental results"

算法 叶片
状态
正常叶片 病变叶片
判断正确 正确率/% 判断正确 正确率/%
本文 早期 4976 99.52 4997 99.94
成熟 4945 98.90 4978 99.56
晚期 4948 98.96 4959 99.18
文献
[2]
早期 4484 89.68 4877 97.54
成熟 4675 93.50 4681 93.62
晚期 4795 95.90 4772 95.44
文献
[3]
早期 4697 93.94 4576 91.52
成熟 4396 87.92 4484 89.68
晚期 4499 89.98 4373 87.46

Table 2

This paper single leaf judgment"

叶片
状态
频域特征 空域特征
CRR/% EER/% CRR/% EER/%
早期 87.56 4.63 99.42 0.75
成熟 99.13 1.08 99.24 0.94
晚期 99.74 0.51 84.76 5.03

Table 3

Disease level"

病变叶占比 病变等级 情况划分
0%~10% 0 正常
10%~20% 1 正常
20%~30% 2 正常
30%~40% 3 轻度病变
40%~50% 4 轻度病变
50%~60% 5 中度病变
60%~70% 6 中度病变
70%~80% 7 中度病变
80%~90% 8 重度病变
90%~100% 9 重度病变

Table 4

Results of early period regional disease testing"

序号 单片数 病变投票 占比/% 病变等级 判断结果
1 5163 21 0.4 0 正常
2 4921 24 0.4 0 正常
3 5215 51 0.9 0 正常
4 5751 102 1.8 0 正常
5 4543 54 1.2 0 正常
6 5642 12 0.2 0 正常
7 6124 13 0.2 0 正常
8 4545 47 1.1 0 正常
9 5437 5345 98.3 9 重度病变
10 5421 5235 96.6 9 重度病变

Table 5

Results of mature period regional disease testing"

序号 单片数 病变投票 占比/% 病变等级 判断结果
1 8457 101 1.2 0 正常
2 7542 71 1.0 0 正常
3 8975 56 0.6 0 正常
4 8876 8450 95.2 9 重度病变
5 8524 512 6 0 正常
6 8945 369 4.1 0 正常
7 9207 1023 11.1 1 正常
8 8752 4235 48.4 4 轻度病变
9 8874 8238 92.8 9 重度病变
10 8785 8452 96.2 9 重度病变

Table 6

Results of late period regional disease testing"

序号 单片数 病变投票 占比/% 病变等级 判断结果
1 6845 745 10.9 1 正常
2 6747 865 12.8 1 正常
3 6572 1204 18.3 1 正常
4 7772 7582 97.6 9 重度病变
5 7578 3354 44.3 4 轻度病变
6 7567 1235 16.3 1 正常
7 7862 4542 57.8 5 中度病变
8 6786 1203 17.7 1 正常
9 8524 8453 99.2 9 重度病变
10 8760 8542 97.5 9 重度病变
[1] 刁智华, 王会丹, 魏伟 . 机器视觉在农业生产中的应用研究[J]. 农机化研究, 2014(3):206-211.
doi: 10.3969/j.issn.1003-188X.2014.03.049
Diao Zhi-hua, Wang Hui-dan, Wei Wei . Summary of research on machine vision application in agricultural production[J]. Journal of Agricultural Mechanization Research, 2014(3):206-211.
doi: 10.3969/j.issn.1003-188X.2014.03.049
[2] 周杰, 潘宏侠, 唐明军 . 一种基于机器视觉特征的农作物病变图像感知方法[J]. 农业与技术, 2017,37(18):5-7.
doi: 10.11974/nyyjs.20170932004
Zhou Jie, Pan Hong-xia, Tang Ming-jun . A method of crop image sensing based on machine vision features[J]. Agriculture & Technology, 2017,37(18):5-7.
doi: 10.11974/nyyjs.20170932004
[3] 潘志国 . 机器视觉技术在农作物病虫害的研究与应用[J]. 电子测试, 2014(5):57-58.
Pan Zhi-guo . Study and application of machine vision technique for the crop diseases and pests of agricultural products[J]. Electronic Test, 2014(5):57-58.
[4] 周晓东, 张雅超, 谭庆昌 , 等. 基于结构光视觉技术的圆柱度测量新方法[J]. 吉林大学学报:工学版, 2017,47(2):524-529.
doi: 10.13229/j.cnki.jdxbgxb201702025
Zhou Xiao-dong, Zhang Ya-chao, Tan Qing-chang , et al. New method of cylindricity measurement based on structured light vision technology[J]. Journal of Jilin University(Engineering and Technology Edition), 2017,47(2):524-529.
doi: 10.13229/j.cnki.jdxbgxb201702025
[5] 李欢利, 郭立红, 王心醉 , 等. 基于加权Gabor滤波器的虹膜识别[J]. 吉林大学学报:工学版, 2014,44(1):196-202.
doi: 10.13229/j.cnki.jdxbgxb201401033
Li Huan-li, Guo Li-hong, Wang Xin-zui , et al. Iris recognition based on weighted Gabor filter[J]. Journal of Jilin University (Engineering and Technology Edition), 2014,44(1):196-202.
doi: 10.13229/j.cnki.jdxbgxb201401033
[6] 陈泠, 高春保, 朱展望 , 等. 小麦黄色素含量与多酚氧化酶活性相关基因的分子标记检测及分布差异[J]. 湖北农业科学, 2017,56(24):4892-4898.
Chen Ling, Gao Chun-bao, Zhu Zhan-wang , et al. Molecular detection and distribution of genes associated with yellow pigment content and polyphenol oxidase activity in wheat cultivars[J]. Hubei Agricultural Sciences, 2017,56(24):4892-4898.
[7] 陈辉皇, 林耀进, 林国平 , 等. 基于邻域粒化的多数据源高投票决策规则的挖掘[J]. 南京大学学报:自然科学版, 2017,53(6):1063-1071.
doi: 10.13232/j.cnki.jnju.2017.06.008
Chen Hui-huang, Lin Yao-jin, Lin Guo-ping , et al. Mining high-voting decision rule based on neighborhood granulation in multiple data sources[J]. Journal of Nanjing University(Natural Sciences), 2017,53(6):1063-1071.
doi: 10.13232/j.cnki.jnju.2017.06.008
[8] Ding Shi-fei, Xu Li, Su Chun-yang , et al. An optimizing method of RBF neural network based on genetic algorithm[J]. Neural Computing and Applications, 2012,21(2):333-336.
doi: 10.1007/s00521-011-0702-7
[9] Sangeetha D, Deepa P. An efficient hardware implementation of canny edge detection algorithm [C]//Proceedings of the IEEE International Conference on VLSI Design, Kolkata, India, 2016: 457-462.
[10] 马秀丽 . 基于数字图像处理的水果表面品质检测方法研究[D]. 沈阳:东北大学信息科学与工程学院, 2011.
Ma Xiu-li . Research on fruit surface quality detection based on digital image processing[D]. Shenyang:College of Information Science and Engineering, Northeast University, 2011.
[1] Nan WANG,Jin⁃bao LI,Yong LIU,Yu⁃jie ZHANG,Ying⁃li ZHONG. TPR⁃TF: time⁃aware point of interest recommendation model based on tensor factorization [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(3): 920-933.
[2] LIU Fu,ZONG Yu-xuan,KANG Bing,ZHANG Yi-meng,LIN Cai-xia,ZHAO Hong-wei. Dorsal hand vein recognition system based on optimized texture features [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1844-1850.
[3] WANG Li-min,LIU Yang,SUN Ming-hui,LI Mei-hui. Ensemble of unrestricted K-dependence Bayesian classifiers based on Markov blanket [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1851-1858.
[4] JIN Shun-fu,WANG Bao-shuai,HAO Shan-shan,JIA Xiao-guang,HUO Zhan-qiang. Synchronous sleeping based energy saving strategy of reservation virtual machines in cloud data centers and its performance research [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1859-1866.
[5] ZHAO Dong,SUN Ming-yu,ZHU Jin-long,YU Fan-hua,LIU Guang-jie,CHEN Hui-ling. Improved moth-flame optimization method based on combination of particle swarm optimization and simplex method [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1867-1872.
[6] OUYANG Dan-tong, FAN Qi. Clause-level context-aware open information extraction [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1563-1570.
[7] LIU Fu, LAN Xu-teng, HOU Tao, KANG Bing, LIU Yun, LIN Cai-xia. Metagenomic clustering method based on k-mer frequency optimization [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1593-1599.
[8] CHE Xiang-jiu, WANG Li, GUO Xiao-xin. Improved boundary detection based on multi-scale cues fusion [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1621-1628.
[9] GUI Chun, HUANG Wang-xing. Network clustering method based on improved label propagation algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1600-1605.
[10] LIU Yuan-ning, LIU Shuai, ZHU Xiao-dong, CHEN Yi-hao, ZHENG Shao-ge, SHEN Chun-zhuang. LOG operator and adaptive optimization Gabor filtering for iris recognition [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1606-1613.
[11] CAO Jie, SU Zhe, LI Xiao-xu. Image annotation method based on Corr-LDA model [J]. 吉林大学学报(工学版), 2018, 48(4): 1237-1243.
[12] ZHAO Hong-wei, LIU Yu-qi, DONG Li-yan, WANG Yu, LIU Pei. Dynamic route optimization algorithm based on hybrid in ITS [J]. 吉林大学学报(工学版), 2018, 48(4): 1214-1223.
[13] HUANG Hui, FENG Xi-an, WEI Yan, XU Chi, CHEN Hui-ling. An intelligent system based on enhanced kernel extreme learning machine for choosing the second major [J]. 吉林大学学报(工学版), 2018, 48(4): 1224-1230.
[14] FU Wen-bo, ZHANG Jie, CHEN Yong-le. Network topology discovery algorithm against routing spoofing attack in Internet of things [J]. 吉林大学学报(工学版), 2018, 48(4): 1231-1236.
[15] HOU Yong-hong, WANG Li-wei, XING Jia-ming. HTTP-based dynamic adaptive streaming video transmission algorithm [J]. 吉林大学学报(工学版), 2018, 48(4): 1244-1253.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] LI Shoutao, LI Yuanchun. Autonomous Mobile Robot Control Algorithm Based on Hierarchical Fuzzy Behaviors in Unknown Environments[J]. 吉林大学学报(工学版), 2005, 35(04): 391 -397 .
[2] Zhang Quan-fa,Li Ming-zhe,Sun Gang,Ge Xin . Comparison between flexible and rigid blank-holding in multi-point forming[J]. 吉林大学学报(工学版), 2007, 37(01): 25 -30 .
[3] Qu Zhao-wei,Chen Hong-yan,Li Zhi-hui,Hu Hong-yu,Wei Wei . 2D view reconstruction method based on single calibration pattern
[J]. 吉林大学学报(工学版), 2007, 37(05): 1159 -1163 .
[4] Wang Li-guo,Zhang Ye,Chen Hao . Spectral unmixing based on robust support vector machine[J]. 吉林大学学报(工学版), 2007, 37(01): 155 -159 .
[5] Xu Si-chuan,Li Rong-qing,Cheng Qin,Guo Ying-nan,Zhang Ji-peng,Sun Ji-mei,Wang Yong-fu . Influence of boundary condition on combustion of ethanol HCCI engine[J]. 吉林大学学报(工学版), 2007, 37(01): 74 -78 .
[6] Shen Chuan-liang,Liu Guo-jun,Dong Jing-shi,Yang Zhi-gang,Cheng Guang-ming . Piezoelectric multi-vibrator and single-chamber pump for precise drug delivery[J]. 吉林大学学报(工学版), 2007, 37(01): 89 -94 .
[7] Shao Bao-dong Sun Zhao-wei,Wang Li-feng . Optimization design of structural size of microchannel cooling heat sink[J]. 吉林大学学报(工学版), 2007, 37(02): 313 -0318 .
[8] Yang Wen, Shi Yong-jiu, Wang Yuan-qing, Shi Gang . Threedimensional finite element analysis on welding residual
stresses of construction steel
[J]. 吉林大学学报(工学版), 2007, 37(02): 347 -0352 .
[9] Cheng Ping,Zhang Hai-tao,Gao Yan,Li Jun-feng,Wang Hong-yan . Application of ANN in property prediction of polyacrylate emulsion
[J]. 吉林大学学报(工学版), 2007, 37(02): 362 -0366 .
[10] Zhang Da-qing;He Qing-hua;Hao Peng;Chen Qian-gen . Robust trajectory tracking control of hydraulic excavator bucket[J]. 吉林大学学报(工学版), 2006, 36(06): 934 -938 .