Performance Analysis of Optimizers for Plant Disease Classification with Convolutional Neural Networks

TL;DR

This paper evaluates the performance of different optimizers in CNN-based plant disease classification, demonstrating that Adam optimizer achieves up to 98% validation accuracy, aiding early disease detection to reduce crop losses.

Contribution

It provides a comparative analysis of optimizers for CNNs in plant disease classification, highlighting the effectiveness of Adam optimizer in this context.

Findings

Adam optimizer achieves 98% validation accuracy

Performance visualized through accuracy, loss, ROC, and confusion matrices

Deep learning can predict plant diseases using satellite, drone, or mobile images

Abstract

Crop failure owing to pests & diseases are inherent within Indian agriculture, leading to annual losses of 15 to 25% of productivity, resulting in a huge economic loss. This research analyzes the performance of various optimizers for predictive analysis of plant diseases with deep learning approach. The research uses Convolutional Neural Networks for classification of farm or plant leaf samples of 3 crops into 15 classes. The various optimizers used in this research include RMSprop, Adam and AMSgrad. Optimizers Performance is visualised by plotting the Training and Validation Accuracy and Loss curves, ROC curves and Confusion Matrix. The best performance is achieved using Adam optimizer, with the maximum validation accuracy being 98%. This paper focuses on the research analysis proving that plant diseases can be predicted and pre-empted using deep learning methodology with the help of satellite, drone based or mobile based images that result in reducing crop failure and agricultural losses.