Predicting Rice Crop Diseases Using CNN Based Image Classification

Abstract

Agriculture is the backbone of global
food security, and rice, being a staple
crop, plays a vital role in feeding a
large portion of the world’s population.
However, rice production is severely
threatened by various rice crop diseases
that reduce yield and quality.
Traditional detection methods rely on
manual observation and expert
knowledge, which are often timeconsuming
and inefficient. To
overcome these limitations, this study
proposes a CNN-based image
classification system for automatic rice
leaf disease detection. The model
processes rice leaf images to classify
them as healthy or diseased with high
accuracy. A diverse dataset of rice
leaves affected by bacterial blight, blast,
and brown spot is used for training and
evaluation. Deep learning techniques
enable effective feature extraction and
precise disease classification without
manual intervention. The system
supports early identification of diseases,
thereby minimizing crop losses and
enhancing productivity. Experimental
results validate the robustness of the
CNN model in real-time detection. This
approach provides a scalable and
efficient solution for smart agriculture,
empowering farmers with reliable
decision-making tools