Classification of selected medicinal plants leaf using image processing

Abstract

Plants are an indispensable part of our ecosystem and the dwindling number of plant varieties is a serious concern. To conserve plants, their rapid identification by botanists is a must, thus a tool is needed which could identify plants using easily available information. There is a growing scientific consensus that plant habitats have been altered and species are disappearing at rates never witnessed before. The biodiversity crisis is not just about the perilous state of plant species but also of the specialists who know them This initially requires data about various plant varieties, so that they could be monitored, protected and can be used for future. Plants form the backbone of Ayurveda and today's Modern day medicine and are a great source of revenue. Due to Deforestation and Pollution, lot of medicinal plant leaves have almost become extinct. So, there is an urgent need for us to identify them and regrow them for the use of future generations. Leaf Identification by mechanical means often leads to wrong identification. Due to growing illegal trade and malpractices in the crude drug industry on one hand and lack of sufficient experts on the other hand, an automated and reliable identification and classification mechanism in order to handle the bulk of data and to curb the malpractices is needed. The following paper aims at implementing such system using image processing with images of the plant leaves as a basis of classification. The software returns the closest match to the query. The proposed algorithm is implemented and the efficiency of the system is found by testing it on 10 different plant species. The software is trained with 100 (10 number of each plant species) leaves and tested with 50 (tested with different plant species) leaves. The efficiency of the implementation of the proposed algorithms is found to be 92%.