ResNet-based approach for Detection and Classification of Plant Leaf Diseases
The process of training ResNet models on an open image dataset provides a sound way towards crop disease detection using automated networks on an enormous global scale.
Abstract
Crop disease is a serious concern for safety of food, but its fast detection still remains difficult in different parts of the world because of the lack of proper infrastructure. Automatic identification of plant diseases is necessary for food security, yield loss estimation and management of disease. With the worldwide increase in digital cameras and continuous improvement in computer vision domain, the automated techniques for detection of disease are highly in demands in precision agriculture, highly productive plant phenotype, smart greenhouse and much more. Working on an open dataset which includes 15200 images of crop leaves, a Residual Network (ResNet34) was trained to perform this task of classification. The proposed ResNet34 model accomplished a 99.40% accuracy on a test set, illustrating the viability of the proposed model. Overall, the process of training ResNet models on an open image dataset provides a sound way towards crop disease detection using automated networks on an enormous global scale.