Detection of Neem Leaf Disease Using Deep Learning Models

Neem is a medicinal plant known for its antibacterial and antifungal properties. However, various leaf diseases affect its growth and medicinal value, making early and accurate detection crucial. Traditional manual inspection methods are time-consuming and error-prone. This research proposes an automated neem leaf disease detection system using deep learning. Five Convolutional Neural Networks (CNNs)ResNet50, DenseNet, MobileNet, GoogleNet, and AlexNetwere evaluated for classifying seven neem leaf categories: Alternaria, Dieback, Leaf Blight, Leaf Miners with Powdery Mildew, Powdery Mildew, and Healthy leaves. A dataset of 1862 images was split into 80 % training and 20 % testing. Images were pre-processed using resizing, normalization, and augmentation to improve model performance. K-Means clustering segmentation was applied to assess its impact on classification by enhancing diseased region detection. Among the tested models, DenseNet achieved the highest accuracy of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 0 \%}$</tex>. This study highlights the potential of deep learning for neem leaf disease detection. Future work will focus on hybrid models and advanced segmentation to enhance classification accuracy and robustness.