Published Paper Details:

The agricultural sector serves as the backbone of a country's innovative growth, providing sustenance and raw materials essential for development. Agriculture is not only vital for human sustenance but also for the provision of resources. Consequently, the detection of leaf diseases has emerged as a critical concern. While traditional methods for identifying leaf diseases exist, they often rely on manual inspection by agriculture professionals or leaf pathologists. This conventional approach is subjective, time-consuming, expensive, and demands extensive expertise and data on leaf diseases. In recent years, advancements in technology have facilitated the use of machine learning and deep learning for leaf disease detection. This study focuses on implementing a Plant Leaf Disease Detection and Classification Network (PDDC-Net) using deep learning models. Pre-processing techniques are applied to eliminate various types of noise and standardize the dataset images. The PDDC-Net utilizes a residual network-based convolutional neural network (ResNet-CNN) for feature extraction and classification. Additionally, the model suggests appropriate pesticides for corresponding plant leaf diseases. Experimental results demonstrate that the proposed PDDC-Net model achieves high accuracy rates in leaf disease detection and classification, marking a significant advancement in agricultural technology.