| Deep Convolutional Neural Networks Approach for Efficient Plant Disease Classification |
| Paper ID : 1049-ISCH |
| Authors |
|
Mourad Raafat * Assistant professor, mathematics department, faculty of science, Helwan university |
| Abstract |
| The early and accurate detection of plant diseases plays a pivotal role in enhancing agricultural productivity and securing global food supplies. Traditional methods of disease identification, which rely on manual inspection by experts, are often subjective, labor-intensive, and impractical for large-scale applications. Recent advancements in Deep Learning (DL), particularly Convolutional Neural Networks (CNNs), have revolutionized image-based disease diagnosis by enabling automatic feature extraction and high-accuracy classification. In this paper, a customized CNN architecture is proposed for multi-class plant disease detection. The architecture integrates multiple convolutional and pooling layers for hierarchical feature learning, dropout layers to mitigate overfitting, and fully connected layers for robust classification. Experimental results, obtained using a comprehensive dataset comprising 38 plant disease categories, demonstrate that the proposed model achieves a test accuracy of 99.21%, substantially outperforming conventional machine learning and baseline CNN approaches. These findings validate the effectiveness and scalability of the proposed framework, positioning it as a promising solution for precision agriculture and automated crop health monitoring. |
| Keywords |
| Deep Learning; Convolutional Neural Networks (CNNs); Plant Disease Detection; Image Classification; Agricultural Technology; Imbalanced Data. |
| Status: Abstract Accepted (Poster Presentation) |