Identification of Medicinal Plant Leaves Using Convolutional Neural Network
Yuanita A. Putri, Esmeralda C. Djamal, Ridwan Ilyas
Abstract
Abstract Medicinal plants (herbs) are plants that are known to have certain compounds which are nutritious for health. In Indonesia there are 30,000 types of plants and 7000 of them are classified as medicinal plants (herbs). The human body is complex and organic, while chemical medicines contain chemicals that are inorganic and pure. Therefore, chemical medicine are considered not very suitable for consumption by the human body, which if consumed continuously can even be bad for human health. However, some chemical drugs are actually symptomatic (temporary) so they must be taken for life by patients with certain diseases. Therefore a system is needed to be able to help the community to recognize medicinal plants better, in this case the medicinal plants are focused on the introduction of medicinal leaves. In this study identification of medicinal plant leaves was carried out using the Convolutional Neural Network method. This research will build a system of identification of medicinal plant leaves by using Convolutional Neural Networks. Using training data that is carried out in a computer set and then implemented in mobile-based software to recognize the types and benefits of medicinal plant leaves identified.