<![CDATA[Medicinal plant leaves hold significant value in health and traditional medicine due to their bioactive compounds, which can be used to treat various diseases. However, identifying and classifying medicinal plant leaves remains challenging due to subtle visual differences that are difficult to recognize manually. Misidentification can hinder the development of herbal medicines and potentially pose risks to users. Therefore, an effective method is needed to accurately classify medicinal plant leaves. The dataset used in this study consists of 3,500 images, which are divided into training, validation, and test sets. The model training process is conducted using the VGG16 architecture, which is known for its effectiveness in feature extraction from images. The training results indicate that the model achieves an accuracy of 97%. Model evaluation is performed using a confusion matrix, which demonstrates that the model effectively distinguishes between 10 classes of medicinal plant leaves. The findings of this study are expected to contribute to the development of a more effective and efficient medicinal plant classification system, making it a potential tool to support decision-making in medicinal leaf classification tasks. This research not only focuses on model development but also highlights the importance of deep learning technology in healthcare, particularly in medicinal plant leaf classificationses.]]>
Copyrights © 2025
