TY  - JOUR
AU  - Gudar Gowthami
AU  - Dudekula Bhanu
AU  - Mangala Bhanu Prakash
AU  - Palyam Kiran Teja
AU  - Chinthalaiah Nani
PY  - 2026
DA  - 2026/04/25
TI  - Deep Convolution Neural Networks for AI Powered Plant Diseases Detection and Diagnosis
JO  - Global Journal of Engineering Innovations and Interdisciplinary Research
VL  - 6
IS  - 4
AB  - Plant disease detection is a crucial aspect of modern agriculture, addressing the challenges caused by
infections that reduce crop yield and quality. This paper presents a novel approach for plant disease
detection and diagnosis using Deep Convolutional Neural Networks (CNN). Leveraging the power of
deep learning, our method aims to improve the accuracy and efficiency of identifying diseases in plant
leaves through image analysis. In the proposed approach, we build upon the foundation of existing
methods that utilize Convolutional Neural Networks and introduce enhancements in data preprocessing,
network architecture, and training strategies. These improvements enable the model to effectively learn
complex patterns such as color variations, texture differences, and structural changes in infected leaves.
We conduct experiments on standard plant leaf image datasets containing multiple classes of healthy and
diseased plants. Our CNN-based approach is compared with traditional machine learning techniques,
demonstrating superior performance in terms of accuracy and reliability. The results show improved
precision and robustness in detecting and classifying plant diseases. This paper not only contributes
to the field of smart agriculture but also highlights the potential of deep learning, particularly CNN, in
solving real-world agricultural problems. The findings open opportunities for future research in disease
localization, real-time field monitoring, and deployment in mobile based applications for farmers.
SN  - 3066-1226
UR  - https://dx.doi.org/10.33425/3066-1226.1282
DO  - 10.33425/3066-1226.1282