Densenet-121 Analysis for Classification of Tomato Leaf Diseases

Tomato leaf disease can lead to financial losses for farmers, as unhealthy tomato leaves can negatively impact the health of tomato fruit. Conventional methods for farmers' identification of tomato leaf diseases are time-consuming and prone to errors, necessitating an accurate classification for plant disease recognition. The DenseNet-121 architecture can help farmers detect leaf diseases early, and farmers can take action in handling them. DenseNet-121 helps the classification process in distinguishing healthy tomato leaves from unhealthy tomato leaves. We use images of tomato leaves as datasets to train the DenseNet-121 model. We evaluate the model using performance metrics like accuracy, precision, and recall after training. We conduct testing to verify the model’s accuracy in classifying tomato leaf diseases. The results showed that the DenseNet-121 architecture achieved a high accuracy of 98.94% in classifying tomato leaf diseases. The main suggestion from this study is that farmers can find leaf diseases early by using feature augmentation and extraction features in the DenseNet-121 architecture for leaf disease classification. We recommend further research to test this model on a larger scale and with different plant types, ensuring its generalizability.