Detecting Leaf Disease and Classifying Images via Transfer Learning with VGG 16

Identifying plant diseases is vital for promoting the robust growth of plants. To maximize agricultural productivity, it is essential to maintain healthy plants and effectively prevent diseases that can compromise them. The adoption of modern technology is becoming paramount to meet the increasing demand for efficient farming practices. Recent improvements in artificial intelligence (AI), machine learning (ML), and deep learning (DL) have significantly transformed agricultural operations, paving the way for enhanced productivity and sustainability in the farming industry. AI significantly boosts productivity, effectively identifies plant diseases, and proactively monitors agricultural air quality. By analyzing plants, machine learning (ML) and deep learning (DL) technologies deliver precise and reliable disease detection. This research paper showcases a cutting-edge system for detecting diseases in tomato leaves, utilizing the pre-trained VGG16 model (Visual Geometry Group-16). Through advanced deep learning techniques, our approach employs three powerful activation functions-Softmax, Rectified Linear Units (ReLU), and Hyperbolic Tangent (Tanh). The results speak for themselves: the Softmax function achieved an impressive accuracy of 97%, while ReLU reached 84%, and Tanh, although less effective, recorded 17%. With such remarkable classification accuracy, our proposed model establishes a robust framework for accurately predicting crop diseases, reducing crop damage, and enhancing plant health.