Agri Watch: Precision Plant Health Monitoring using Deep Learning

Abstract

The growth of deep learning technologies allows us to achieve higher accuracy in the classification of plant diseases, as well as in other domains. This research reveals the performance of several DL approaches, including custom convolutional neural networks (CNNs) and models which are pre-trained namely VGG16 and ResNet34, which were used for the recognition of diseases in plants that are depicted through the images. These models may obtain the necessary growing environment for training and assessing the models by using a publicly accessible dataset that includes pictures of both healthy and diseased plants, in total there are 14 unique plants used. The results of the experiment suggest that all the models combinedly gave 98.46% accuracy in the classification of diverse plant diseases. In addition to this, the paper discusses the hyperparameters like learning rate and optimizer choice that affect the model furthermore, the project discusses the methods involved in training deep learning models on GPU devices computationally speaking. Thereby, this project can be added to the field of agriculture vision by showing that deep learning methods are good for plant disease classification.

Keywords

• accuracy
• hyperparameters
• optimizer
• crop management
• gpu computing
• agriculture vision