Early detection and identification of grape diseases using convolutional neural networks

• Published in: Journal of plant diseases and protection (2006) 2022-06, Vol.129 (3), p.521-532
• Main Authors: Math, RajinderKumar M., Dharwadkar, Nagaraj V.
• Format: Article
• Language: English
• Subjects: Biomedical and Life Sciences; Life Sciences; Original Article; Plant Pathology; Plant Physiology; Plant Sciences
• ISSN: 1861-3829; 1861-3837
• DOI: 10.1007/s41348-022-00589-5

Crop protection aims to develop an agriculture system that is resilient to common agricultural threats like diseases, pests, and weeds that result in sub-optimal growth of crops in terms of quality and quantity. Therefore, timely disease detection and identification is a crucial concern for farmers across the globe. At present, crop diseases are identified by farmers manually, which is time-consuming, subjective, and also error-prone due to human involvement. The early disease identification and detection would help the farmers reduce the use of pesticides, minimizing the environmental footprint while increasing the profits by reducing the losses. To precisely identify the crop diseases at the initial stages, the machine learning (ML) algorithms or, in more precise, deep learning (DL) algorithms are very helpful. The research aims to develop a deep convolutional neural network (DCNN) model to identify and classify grape diseases based on the RGB leaf images. The proposed model uses an image dataset of grape crops from the Plant Village dataset publicly available for researchers and engineers. The specialty of the developed model is that the CNN classification model is built from scratch that provides accuracy close to or even more significant than the accuracy obtained for some pre-trained models using transfer learning. The model achieved an accuracy of 99.34% and equal values for precision, recall, and an F1 score of 0.9934. These results indicate models’ capability to accurately identify and classify grapes’ common diseases based on the RGB leaf images. The trained model is converted and saved in TensorFlow tflite format, and it can be readily deployed to mobile devices to provide real-time disease identification in precision agriculture (PA) application.