Imperial College London
Portrait Picture

ProfessorArnabMajumdar

Faculty of Engineering, Department of Civil and Environmental Engineering

Professor of Transport Risk and Safety
 
 
 
//

Contact

 

+44 (0)20 7594 6037a.majumdar

 
 
//

Assistant

 

Ms Maya Mistry +44 (0)20 7594 6100

 
//

Location

 

604Skempton BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Abbas:2022:10.32604/cmc.2023.028824,
author = {Abbas, S and Attique, Khan M and Alhaisoni, M and Tariq, U and Armghan, A and Alenezi, F and Majumdar, A and Thinnukool, O},
doi = {10.32604/cmc.2023.028824},
journal = {Computers, Materials and Continua},
pages = {1139--1159},
title = {Crops leaf diseases recognition: a framework of optimum deep learning features},
url = {http://dx.doi.org/10.32604/cmc.2023.028824},
volume = {74},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Manual diagnosis of crops diseases is not an easy process; thus, a computerized method is widely used. From a couple of years, advancements in the domain of machine learning, such as deep learning, have shown substantial success. However, they still faced some challenges such as similarity in disease symptoms and irrelevant features extraction. In this article, we proposed a new deep learning architecture with optimization algorithm for cucumber and potato leaf diseases recognition. The proposed architecture consists of five steps. In the first step, data augmentation is performed to increase the numbers of training samples. In the second step, pre-trained DarkNet19 deep model is opted and fine-tuned that later utilized for the training of fine-tuned model through transfer learning. Deep features are extracted from the global pooling layer in the next step that is refined using Improved Cuckoo search algorithm. The best selected features are finally classified using machine learning classifiers such as SVM, and named a few more for final classification results. The proposed architecture is tested using publicly available datasets–Cucumber National Dataset and Plant Village. The proposed architecture achieved an accuracy of 100.0%, 92.9%, and 99.2%, respectively. A comparison with recent techniques is also performed, revealing that the proposed method achieved improved accuracy while consuming less computational time.
AU  - Abbas,S
AU  - Attique,Khan M
AU  - Alhaisoni,M
AU  - Tariq,U
AU  - Armghan,A
AU  - Alenezi,F
AU  - Majumdar,A
AU  - Thinnukool,O
DO  - 10.32604/cmc.2023.028824
EP  - 1159
PY  - 2022///
SN  - 1546-2218
SP  - 1139
TI  - Crops leaf diseases recognition: a framework of optimum deep learning features
T2  - Computers, Materials and Continua
UR  - http://dx.doi.org/10.32604/cmc.2023.028824
UR  - https://www.techscience.com/cmc/v74n1/49776
UR  - http://hdl.handle.net/10044/1/101724
VL  - 74
ER  -
Download