Detecting Bakanae disease in rice seedlings by machine vision

被引:95
作者
Chung, Chia-Lin [1 ]
Huang, Kai-Jyun [2 ]
Chen, Szu-Yu [1 ]
Lai, Ming-Hsing [3 ]
Chen, Yu-Chia [4 ]
Kuo, Yan-Fu [2 ]
机构
[1] Natl Taiwan Univ, Dept Plant Pathol & Microbiol, Taipei 106, Taiwan
[2] Natl Taiwan Univ, Dept Bioind Mechatron Engn, 1,Sect 4,Roosevelt Rd, Taipei 106, Taiwan
[3] Agr Res Inst Taiwan, Crop Sci Div, Taichung, Taiwan
[4] Natl Taiwan Univ, Master Program Plant Med, Taipei 106, Taiwan
关键词
Foolish seedling; Fusarium fujikuroi; Disease screening; Early detection; Image processing; Machine learning; PATHOGENICITY; FUJIKUROI;
D O I
10.1016/j.compag.2016.01.008
中图分类号
S [农业科学];
学科分类号
09 ;
摘要
Bakanae disease, or "foolish seedling", is a seed-borne disease of rice (Oryza sativa L.). Infected plants can yield empty panicles or perish, resulting in a loss of grain yield. The disease occurs most frequently when contaminated seeds are used. Once the seeds are contaminated, the pathogen Fusarium fujikuroi spreads in the field. Therefore, infected plants must be screened at early developmental stages. This work proposes an approach to nondestructively distinguish infected and healthy seedlings at the age of 3 weeks using machine vision. Seeds of the rice cultivars Tainan 11 and Toyonishiki were inoculated with a conidial suspension of F. fujikuroi. The seedling were cultivated in an incubator for 3 weeks. The images of infected and control seedlings were acquired using flatbed scanners to quantify their morphological and color traits. Support vector machine (SVM) classifiers were developed for distinguishing the infected and healthy seedlings. A genetic algorithm was used for selecting essential traits and optimal model parameters for the SVM classifiers. The proposed approach distinguished infected and healthy seedlings with an accuracy of 87.9% and a positive predictive value of 91.8%. (C) 2016 Elsevier B.V. All rights reserved.
引用
收藏
页码:404 / 411
页数:8
相关论文
共 28 条
[1]   Molecular identification of Fusarium spp. associated with bakanae disease of rice in Italy and assessment of their pathogenicity [J].
Amatulli, M. T. ;
Spadaro, D. ;
Gullino, M. L. ;
Garibaldi, A. .
PLANT PATHOLOGY, 2010, 59 (05) :839-844
[2]   A survey of cross-validation procedures for model selection [J].
Arlot, Sylvain ;
Celisse, Alain .
STATISTICS SURVEYS, 2010, 4 :40-79
[3]   Digital image processing techniques for detecting, quantifying and classifying plant diseases [J].
Arnal Barbedo, Jayme Garcia .
SPRINGERPLUS, 2013, 2 :1-12
[4]  
Celis J.E., 2005, Cell Biology: A Laboratory Handbook
[5]   LIBSVM: A Library for Support Vector Machines [J].
Chang, Chih-Chung ;
Lin, Chih-Jen .
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)
[6]  
Holland JH., 1992, ADAPTATION NATURAL A, DOI [10.7551/mitpress/1090.001.0001, DOI 10.7551/MITPRESS/1090.001.0001]
[7]  
Hossain KS, 2013, BANGL J BOT, V42, P315
[8]  
Hsu C. C., 2013, Plant Pathology Bulletin, V22, P291
[9]  
Hsu C.W., 2003, PRACTICAL GUIDE SUPP
[10]   A GA-based feature selection and parameters optimization for support vector machines [J].
Huang, Cheng-Lung ;
Wang, Chieh-Jen .
EXPERT SYSTEMS WITH APPLICATIONS, 2006, 31 (02) :231-240