Weed Disease Classification using CNN and Inception V3 Model

The identification and regulating of weed diseases in modern agriculture is very significant because it is a direct factor that may influence crop quality and productivity. To advance the clinical precision and effectiveness of weeds diseases identification, this research focuses on the incorporation of the Inception V3 model with the Convolutional Neural Network (CNN). Once trained on a large number of pictures of weeds at a high-resolution level, the model then reached an amazing accuracy rate of 92%Augmentation and normalization were some of the key preprocessing techniques used to improve model performance by 8%. Proposed system is a highly efficient tool for early-stage disease detection in precision farming, which is far more competent than conservative methodology by a lot. More advanced meta-learning and reinforcement learning approaches can be combined further to enhance model accuracy and flexibility which will be an area of interest for future research