Crop Disease Detection Using Deep Learning Techniques on Images
- 1 School of Engineering and Computer Science, Laurentian University, Sudbury, Ontario, Canada
- 2 Department of Biotechnology, Jaypee Institute of Information Technology, A-10, Sector-62, Noida, Uttar Pradesh,, India
Abstract
Agriculture plays a crucial role in the economic development of many countries and sustains the global population despite facing various challenges like climate change, pollinator decline, and plant diseases. These threats to food security highlight the need for innovative solutions to prevent crop loss. Leveraging smartphone technology for automated image recognition-based disease diagnosis has emerged as a promising approach, thanks to their computing power and high-resolution cameras. To address this issue, we have focused on deep learning-based image detection techniques to identify plant diseases using the "PlantVillage" dataset. Several deep learning architectures, including AlexNet, GoogleNet, ResNet50, and InceptionV3, were employed and trained using two approaches: 'Training from scratch' and 'transfer learning’. The results of the analysis reveal GoogLeNet architecture achieved the highest accuracy of 0.999 for color images and 0.996 for segmented images, whereas InceptionV3 trained from scratch gave the highest accuracy of 0.994 for grayscale images with a train-test ratio of 90:10. All the models trained from scratch achieved the maximum F1-score of 1.0 for color and segmented images whereas for grayscale images, GoogleNet and InceptionV3 achieved the highest F1-score of 0.999 with train-test ratio 90:10. These findings indicate the potential of deep learning methods in detecting and diagnosing plant diseases, which can significantly enhance the efficiency and accuracy of disease diagnosis processes in agriculture. Further research and improvements in image recognition techniques can lead to more robust and effective solutions for securing global food production.
DOI: https://doi.org/10.3844/jcssp.2023.1438.1449
Copyright: © 2023 Kinjal Vijaybhai Deputy, Kalpdrum Passi and Chakresh Kumar Jain. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
- 1,795 Views
- 1,372 Downloads
- 2 Citations
Download
Keywords
- Machine Learning
- Deep Learning
- Crop Disease
- Agriculture
- Image Detection