Attention-Based Recurrent Neural Network for Plant Disease Classification

被引:42
作者
Lee, Sue Han [1 ]
Goeau, Herve [2 ,3 ]
Bonnet, Pierre [2 ,3 ]
Joly, Alexis [4 ]
机构
[1] Swinburne Univ Technol, Sarawak Campus, Kuching, Malaysia
[2] Univ Montpellier, AMAP, CIRAD, CNRS,INRA,IRD, Montpellier, France
[3] UMR AMAP, CIRAD, Montpellier, France
[4] INRIA Sophia Antipolis ZENITH Team, URMM UMR 5506, Montpellier, France
关键词
plant disease classification; deep learning; recurrent neural network; automated visual crops analysis; precision agriculture technologies; crops monitoring; pests analysis; smart farming; ACTION RECOGNITION;
D O I
10.3389/fpls.2020.601250
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
Plant diseases have a significant impact on global food security and the world's agricultural economy. Their early detection and classification increase the chances of setting up effective control measures, which is why the search for automatic systems that allow this is of major interest to our society. Several recent studies have reported promising results in the classification of plant diseases from RGB images on the basis of Convolutional Neural Networks (CNN). These studies have been successfully experimented on a large number of crops and symptoms, and they have shown significant advantages in the support of human expertise. However, the CNN models still have limitations. In particular, CNN models do not necessarily focus on the visible parts affected by a plant disease to allow their classification, and they can sometimes take into account irrelevant backgrounds or healthy plant parts. In this paper, we therefore develop a new technique based on a Recurrent Neural Network (RNN) to automatically locate infected regions and extract relevant features for disease classification. We show experimentally that our RNN-based approach is more robust and has a greater ability to generalize to unseen infected crop species as well as to different plant disease domain images compared to classical CNN approaches. We also analyze the focus of attention as learned by our RNN and show that our approach is capable of accurately locating infectious diseases in plants. Our approach, which has been tested on a large number of plant species, should thus contribute to the development of more effective means of detecting and classifying crop pathogens in the near future.
引用
收藏
页数:8
相关论文
共 29 条
[1]  
Abadi M, 2016, ACM SIGPLAN NOTICES, V51, P1, DOI [10.1145/2951913.2976746, 10.1145/3022670.2976746]
[2]  
Atabay Habibollah Agh, 2017, Journal of Theoretical and Applied Information Technology, V95, P6800
[3]   Smart Farming: Pomegranate Disease Detection Using Image Processing [J].
Bhange, Manisha ;
Hingoliwala, H. A. .
SECOND INTERNATIONAL SYMPOSIUM ON COMPUTER VISION AND THE INTERNET (VISIONNET'15), 2015, 58 :280-288
[4]  
Brahimi M, 2018, HUM-COMPUT INT-SPRIN, P93, DOI 10.1007/978-3-319-90403-0_6
[5]   Recurrent Spatial-Temporal Attention Network for Action Recognition in Videos [J].
Du, Wenbin ;
Wang, Yali ;
Qiao, Yu .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (03) :1347-1360
[6]  
Durmus H, 2017, INT CONF AGRO-GEOINF, P46
[7]   Current and Prospective Methods for Plant Disease Detection [J].
Fang, Yi ;
Ramasamy, Ramaraja P. .
BIOSENSORS-BASEL, 2015, 5 (03) :537-561
[8]   Deep learning models for plant disease detection and diagnosis [J].
Ferentinos, Konstantinos P. .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2018, 145 :311-318
[9]   Deep Learning-Based Phenotyping System With Glocal Description of Plant Anomalies and Symptoms [J].
Fuentes, Alvaro ;
Yoon, Sook ;
Park, Dong Sun .
FRONTIERS IN PLANT SCIENCE, 2019, 10
[10]   A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition [J].
Fuentes, Alvaro ;
Yoon, Sook ;
Kim, Sang Cheol ;
Park, Dong Sun .
SENSORS, 2017, 17 (09)