Deep Learning-Based Wheat Disease Detection and Classification
System Using Convolutional Neural Networks
Ms. Drashti Shah1, Mr. Dhruv Chauhan2, Dr (Mrs). Mahasweta Joshi3
1,2B. Tech Computer Engineering, Birla Vishvakarma Mahavidyalaya (BVM) Engineering College, V. V.
Nagar, India,
3Assistant Professor, Computer Department, Birla Vishvakarma Mahavidyalaya (BVM) Engineering
College, V. V. Nagar, India
Received: 04 December 2025; Accepted: 10 December 2025; Published: 19 December 2025
ABSTRACT
Wheat, one of the major crops in the world, is vulnerable to many diseases that cause tremendous yield and
quality loss. This paper proposes a deep learning method for the automatic detection and classification of wheat
diseases based on a Convolutional Neural Network (CNN). We respond to the imperative of early and precise
identification of diseases in wheat crops in order to reduce agricultural losses.The system learned on a data set
of more than 14,000 wheat leaf images corresponding to 15 classes of various rusts, blights, insects, and normal
leaves. Our suggested CNN model reached a training accuracy of 97.02% and validation accuracy of 91.00%.
The model design uses data augmentation strategies and dropout regularization to promote generalization as
well as avoid overfitting
In addition, we created a friendly, web-based platform based on Streamlit that combines the trained model with
a MySQL database for real-time disease detection and recommendation of corresponding treatments. The
outcomes show the efficacy and practicality of deep learning in contemporary agricultural disease management,
offering farmers and agricultural specialists a worthwhile resource.
Keywords: Wheat Disease Detection, Deep Learning, Convolutional Neural Network (CNN), Agricultural
Technology, Image Classification, Plant Pathology.
INTRODUCTION
Wheat is one of the most cultivated cereal crops and is a food staple for more than one billion people worldwide.
Yet wheat is constantly being threatened by a vast range of pathogens (fungi, bacteria, viruses) and insects,
which can lower both yield (volume) and grain quality. Of those, fungal diseases (rusts, mildews, blotches, root
rots) are particularly destructive. Worldwide economic losses due to wheat rusts alone amount to billions of
dollars per year.[11].
There are also viral diseases. Wheat streak mosaic virus (WSMV) and wheat dwarf virus (WDV), for instance,
can induce severe yield losses and stunting. Leaf blight in India, caused by the fungus Alternaria triticina, is
critical: under heavy infection, yield loss of up to 60 % has been observed. [12].
The recent advancements in artificial intelligence, particularly in computer vision and deep learning, offer
powerful solutions to these challenges. Convolutional Neural Networks (CNNs), a class of deep neural networks,
are exceptionally well-suited for image analysis tasks and have demonstrated remarkable success in image
classification. This research leverages CNNs to develop a comprehensive system for wheat disease detection
that can accurately classify 15 different types of diseases and healthy plant conditions from leaf images. The
system extends beyond simple classification by integrating the predictive model into a practical web application
that provides users with suggested treatment measures from a connected database, creating a complete end-to-
end diagnostic tool.
Page 954
