Identifying medicinal plants and understanding their properties is crucial for advancing healthcare and preserving traditional knowledge. However, traditional methods of plant identification are often time-consuming and reliant on expert knowledge. This study proposes a deep learning-based approach for automatically recognizing medicinal plants from images and providing information about their medicinal properties. Leveraging a custom dataset of 500 images across 8 plant species, we trained a Convolutional Neural Network (CNN) with a twolayer convolutional architecture, complemented by max-pooling, dense, and dropout layers. After training for 30 epochs, the model achieved a training accuracy of 91.47% and a validation accuracy of 90.5%, demonstrating its effectiveness in plant classification tasks, consistent with findings from prior research. These results highlight the potential of deep learning models to assist both experts and non-experts in plant identification and facilitate access to valuable information about medicinal benefits. Future work will focus on improving the model’s robustness and extending its application to real-time plant identification systems.