Pakistan Science Abstracts
Article details & metrics
No Detail Found!!
Sooty mold disease detection on cotton leaves using deep learning
Author(s):
1. Sadia Rasheed: Department of Computer Science, MNS-University of agriculture Multan, Pakistan
2. Javeria Jabeen: Department of Computer Science, MNS-University of agriculture Multan, Pakistan
3. Ayesha Hakim: Department of Computer Science, MNS-University of agriculture Multan, Pakistan
4. Ali Imran: Department of Agribusiness and Applied Economics MNSUA, Multan, Pakistan
5. Mirza Abid Mehmood: Department of Plant Pathology, MNS University of agriculture Multan, Pakistan
6. Manal Ahmad: Department of Computer Science, MNS-University of agriculture Multan, Pakistan
Abstract:
Agriculture in Pakistan is among the sectors that play an important role in country's economic growth. Cotton is a cash crop, Pakistan being the sixth largest producer in world ranking. Pest and diseases largely impact crop production and total yield. Sooty mold is the one of disease that attack on cotton leaves. The usage of chemical fertilizers and pesticides may be reduced and the spread of cotton leaf diseases can be controlled by early detection and diagnosis. This study proposes the utilization of a deep learning model to detect sooty mold disease in cotton leaves. To develop an accurate detection system, a dataset consisting of images of both sooty mold-affected and healthy cotton leaves was collected from cotton crop fields at MNS- University of Agriculture. Preprocessing is applied, including resizing and rescaling. Two deep learning models, namely VGG-16 and Xception, were trained using a transfer learning approach. The results demonstrate an exceptional accuracy rate of 99.81% achieved by the VGG-16 model in automatically detecting sooty mold disease. This study holds significant promise for assisting farmers by enabling the early detection of sooty mold in cotton leaves. Timely information regarding the presence of the disease empowers farmers to promptly implement appropriate measures to protect their crops.
Page(s): 84-84
DOI: DOI not available
Published: Journal: Abstract Book on International Conference on Food and Applied Sciences (ICFAS-23) 3-5 August 23, Volume: 0, Issue: 0, Year: 2023
Keywords:
deep learning , VGG16 , Xception , Cotton Leaf Disease , Sooty mold
References:
References are not available for this document.
Citations
Citations are not available for this document.
0

Citations

0

Downloads

35

Views