Tomato Leaf Disease Prediction using Neural Networks

Tomatoes, which are extensively grown in Indian agricultural fields, are among the commonly cultivated vegetable crops. The tropical climate in India provides favorable conditions for tomato cultivation. However, various factors, including climatic conditions and other elements, can adversely affect the normal growth of tomato plants. Plant diseases present a significant risk to crop production and can lead to economic losses, adding to the challenges posed by climate conditions and natural disasters. Unfortunately, traditional methods of detecting diseases in tomato crops have proven to be ineffective and time-consuming. This study primarily aims to accurately identify tomato plant leaf diseases that are found using image analysis. Various methods have been applied for extracting the features that have been used to improve the accuracy of classification. Alex Net, InceptionV3, and a CNN (Conv Net) algorithm have been utilized to classify many types of tomato plant diseases. When comparing the results, it is notable that the CNN (Conv Net) classifier outperforms the other two models. The findings demonstrate the practical applicability of the model in real-life scenarios