Medicinal plants have been utilized for centuries, and their importance in the healthcare industry is growing. Yet, manually classifying and identifying medicinal plants may be time-consuming and blunder. To label this issue, this project proposes the development of a vision-based system for accurate identification and classification of various medicinal plant species using the Inception V3 model. The system uses deep convolutional neural networks to learn and extract relevant features and patterns that distinguish different species from the large dataset of images of various medicinal plants. To enhance the system’s accuracy and robustness, several image preprocessing and feature extraction techniques are employed. The effectiveness of the proposed system will be assessed using a variety of metrics, such as recall, accuracy, precision, and F1-score. Our proposed system achieves good accuracy of 93.3%. The system’s potential applications include identifying medicinal plants in natural environments, tracking plant growth, and monitoring plant diseases. The proposed vision-based system has the potential to provide an accurate and efficient solution for identifying and classifying medicinal plants, contributing to the fields of botany, agriculture, and medicine.