文章基本信息

标题：Identification of Multiple Leaves and Retrieval of its Medicinal Value
本地全文：下载
作者：Nisha Jenifer Roche ; Dr.Jharna Majumdar ; Shilpa Ankalaki 等
期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：7
DOI：10.15680/ijircce.2015.03071131
出版社：S&S Publications
摘要：Earth has a large part of flora diversity. However globalization has adversely affected our environmentand much of the plants are on the verge of extinction. The chemical compounds present in plants works in a similarmanner to that of man-made drugs. As this field is growing, it becomes utmost important to keep the database of plantsupdated so that identification of plants can be done smoothly. This paper proposes an efficient method to detectmultiple leaves called the Component Labeling Method. Shape features which are invariant to translation, rotation andscaling are considered. In addition to the existing basic shape features new features which are also invariant have beenconsidered. The features in the feature database are grouped by using an efficient clustering method called CURE andfinally the leaves are identified. Accuracy of the leaves identified using basic features and the new features are alsoshown.
关键词：Component Labeling Method; translation; rotation and scaling; CURE Clustering Method