Automatic Detection of Citrus Fruit and Leaves Diseases Using Deep Neural Network Model

被引:78
作者
Khattak, Asad [1 ]
Asghar, Muhammad Usama [2 ]
Batool, Ulfat [2 ]
Asghar, Muhammad Zubair [2 ]
Ullah, Hayat [2 ]
Al-Rakhami, Mabrook [3 ]
Gumaei, Abdu [3 ]
机构
[1] Zayed Univ, Coll Technol Innovat, Dubai, U Arab Emirates
[2] Gomal Univ, Inst Comp & Informat Technol, Dera Ismail Khan 29220, KP, Pakistan
[3] King Saud Univ, Coll Comp & Informat Sci, Informat Syst Dept, Res Chair Pervas & Mobile Comp, Riyadh 11362, Saudi Arabia
关键词
Diseases; Deep learning; Feature extraction; Agriculture; Support vector machines; Neural networks; Image color analysis; Citrus leaf diseases; citrus fruit diseases detection; convolutional neural network; deep learning; CLASSIFICATION; SYSTEM; CANKER;
D O I
10.1109/ACCESS.2021.3096895
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Citrus fruit diseases are the major cause of extreme citrus fruit yield declines. As a result, designing an automated detection system for citrus plant diseases is important. Deep learning methods have recently obtained promising results in a number of artificial intelligence issues, leading us to apply them to the challenge of recognizing citrus fruit and leaf diseases. In this paper, an integrated approach is used to suggest a convolutional neural networks (CNNs) model. The proposed CNN model is intended to differentiate healthy fruits and leaves from fruits/leaves with common citrus diseases such as black spot, canker, scab, greening, and Melanose. The proposed CNN model extracts complementary discriminative features by integrating multiple layers. The CNN model was checked against many state-of-the-art deep learning models on the Citrus and PlantVillage datasets. According to the experimental results, the CNN Model outperforms the competitors in a variety of measurement metrics. The CNN Model has a test accuracy of 94.55 percent, making it a valuable decision support tool for farmers looking to classify citrus fruit/leaf diseases.
引用
收藏
页码:112942 / 112954
页数:13
相关论文
共 42 条
[1]   Classification of Poetry Text Into the Emotional States Using Deep Learning Technique [J].
Ahmad, Shakeel ;
Asghar, Muhammad Zubair ;
Alotaibi, Fahad Mazaed ;
Khan, Sherafzal .
IEEE ACCESS, 2020, 8 :73865-73878
[2]   An efficient approach for sub-image separation from large-scale multi-panel images using dynamic programming [J].
Ali, Mushtaq ;
Asghar, Muhammad Zubair ;
Baloch, Amanullah .
MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (04) :5449-5471
[3]  
Ayepah K., 2019, 2019 25 IEEE INT C, P1
[4]   Comparison of convolution neural networks for smartphone image based real time classification of citrus leaf disease [J].
Barman, Utpal ;
Choudhury, Ridip Dev ;
Sahu, Diganto ;
Barman, Golap Gunjan .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2020, 177 (177)
[5]   Deep learning for pedestrian collective behavior analysis in smart cities: A model of group trajectory outlier detection [J].
Belhadi, Asma ;
Djenouri, Youcef ;
Srivastava, Gautam ;
Djenouri, Djamel ;
Lin, Jerry Chun-Wei ;
Fortino, Giancarlo .
INFORMATION FUSION, 2021, 65 :13-20
[6]   Pest identification via deep residual learning in complex background [J].
Cheng, Xi ;
Zhang, Youhua ;
Chen, Yiqiong ;
Wu, Yunzhi ;
Yue, Yi .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2017, 141 :351-356
[7]   Distribution equalization learning mechanism for road crack detection [J].
Fang, Jie ;
Qu, Bo ;
Yuan, Yuan .
NEUROCOMPUTING, 2021, 424 :193-204
[8]  
Golhani Kamlesh, 2018, Information Processing in Agriculture, V5, P354, DOI 10.1016/j.inpa.2018.05.002
[9]  
Hamarneh, ARXIV200212351
[10]  
Hughes D., 2015, An open access repository of images on plant health to enable the development of mobile disease diagnostics