Hyperspectral Leaf Image-Based Cucumber Disease Recognition Using the Extended Collaborative Representation Model

被引:14
作者
Li, Yuhua [1 ]
Luo, Zhihui [1 ]
Wang, Fengjie [1 ]
Wang, Yingxu [1 ]
机构
[1] Nanjing Agr Univ, Coll Engn, Nanjing 210031, Peoples R China
基金
中国国家自然科学基金; 中国博士后科学基金;
关键词
cucumber disease recognition; hyperspectral imaging; extended collaborative representation (ECR); spectral library; FACE RECOGNITION; CLASSIFICATION; IDENTIFICATION;
D O I
10.3390/s20144045
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Collaborative representation (CR)-based classification has been successfully applied to plant disease recognition in cases with sufficient training samples of each disease. However, collecting enough training samples is usually time consuming and labor-intensive. Moreover, influenced by the non-ideal measurement environment, samples may be corrupted by variables introduced by bad illumination and occlusions of adjacent leaves. Consequently, an extended collaborative representation (ECR)-based classification model is presented in this paper. Then, it is applied to cucumber leaf disease recognition, which constructs a pure spectral library consisting of several representative samples for each disease and designs a universal variation spectral library that deals with linear variables superimposed on samples. Thus, each query sample is encoded as a linear combination of atoms from these two spectral libraries and disease identity is determined by the disease of minimal reconstruction residuals. Experiments are conducted on spectral curves extracted from normal leaves and the disease lesions of leaves infected with cucumber anthracnose and brown spot. The diagnostic accuracy is higher than 94.7% and the average online diagnosis time is short, about 1 to 1.3 ms. The results indicate that the ECR-based classification model is feasible in the fast and accurate diagnosis of cucumber leaf diseases.
引用
收藏
页数:13
相关论文
共 33 条
[1]  
[Anonymous], 2013, T CHIN SOC AGR ENG
[2]   An Investigation Into Machine Learning Regression Techniques for the Leaf Rust Disease Detection Using Hyperspectral Measurement [J].
Ashourloo, Davoud ;
Aghighi, Hossein ;
Matkan, Ali Akbar ;
Mobasheri, Mohammad Reza ;
Rad, Amir Moeini .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2016, 9 (09) :4344-4351
[3]   Identification of Cucumber Disease Using Hyperspectral Imaging and Discriminate Analysis [J].
Chai A-li ;
Liao Ning-fang ;
Tian Li-xun ;
Shi Yan-xia ;
Li Bao-ju .
SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30 (05) :1357-1361
[4]   Extended SRC: Undersampled Face Recognition via Intraclass Variant Dictionary [J].
Deng, Weihong ;
Hu, Jiani ;
Guo, Jun .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (09) :1864-1870
[5]   Robust face recognition via hierarchical collaborative representation [J].
Duc My Vo ;
Lee, Sang-Woong .
INFORMATION SCIENCES, 2018, 432 :332-346
[6]  
El-Helly M., 2003, IICAI, P1182
[7]   Deep learning models for plant disease detection and diagnosis [J].
Ferentinos, Konstantinos P. .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2018, 145 :311-318
[8]   Semi-Supervised Sparse Representation Based Classification for Face Recognition With Insufficient Labeled Samples [J].
Gao, Yuan ;
Ma, Jiayi ;
Yuille, Alan L. .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (05) :2545-2560
[9]   Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning [J].
Gao, Zongmei ;
Shao, Yuanyuan ;
Xuan, Guantao ;
Wang, Yongxian ;
Liu, Yi ;
Han, Xiang .
ARTIFICIAL INTELLIGENCE IN AGRICULTURE, 2020, 4 :31-38
[10]   Collaborative representation with HM-LBP features for palmprint recognition [J].
Guo, Xiumei ;
Zhou, Weidong ;
Zhang, Yanli .
MACHINE VISION AND APPLICATIONS, 2017, 28 (3-4) :283-291