Identification of Herbal Plants using CNN

Abstract: Plants were also essential to human life because they provide us with air, food, shelter, medicine, fuel, and gums that help to preserve the environment. Many plants have valuable medicinal properties and active components that can be used in medicines. Many beneficial plant species are currently becoming extinct or being destroyed as a result of factors such as global warming, rising population, professional secrecy, a lack of government awareness for research operations, and a lack of knowledge about therapeutic plants. Because manual identification of medicinal plants takes a long time, professional help is required. The automatic identification of medicinal plants is a hot topic in image processing research right now. We created our own dataset of 4 categories of herbal plants for experimental investigation, including cinnamon, henna, marigold, and turmeric, and we also used an existing Malaysian flavia dataset. We created a leaf and flower identification technique that uses a CNN classifier and has a 95% accuracy.

Keywords: Image processing, Herbal plant, CNN, leaf and flower