Medicinal Plants Classification by VisualCharacteristics of Leaves Using CNN

Identification of medicinal plants correctly is crucial in Ayurvedic medicine. By their visual characteristics and scent, plants are recognized by human experts. Negative effects could come from incorrectly identifying therapeutic herbs. Using visual morphological traits like the size, color, and texture of the leaves and flowers, it is possible to automate the identification of plants. In this study, we demonstrate the use of machine learning and image processing to identify uncommon medicinal plants with high accuracy. The leaves and petals of rare medicinal plants used in Ayurvedic medicine were scanned and turned into a database for this study. Images were captured of both the anterior and posterior sides of leaves and flowers. According to their distinct feature combination, leaves are categorized. The success rates of identifying plants have been found to be as high as 98% in testing.