Computer Based Taxonomy in The Identification of Ethno-Medicinal Plants of Shakumbhari Devi of Shiwalik Hills

Indigenous medicinal plants are important component of traditional knowledge. Monumental scriptures provide a unique source for several medicinal plants. Many medicinal plant species were used by the mankind since historic times for the treatment and prevention of diseases. Medicinal plant species were found to be used in fever, diarrhoea and dysentery. Roots, rhizomes, leaves and stem barks are mostly used in the form of juice, raw items, paste and decoction of plants. Due to thegreat medicinal importance, malpractices like adulterations of these medicinal plants and their parts have become common. The purpose of this study was to collect information about the interaction of various communities (Van Gujjars, Saints and Ojhas) of the area with plant wealth and develop a computer aided software technique for the correct, quick, easy and authentic identification of these medicinal plants and their parts. Plant recognition is an important and challenging task. Leaf recognition plays an important role in plant recognition and its key issue lies in whether selected features are stable and have good ability to discriminate different kinds of leaves. From the view of plant leaf morphology (such as shape, and color), domainrelated visual features of plant leaf are analyzed and extracted. On this basis, an approach for recognizing plant leaf using a software using Content Based Image Retrieval (CBIR) is developed and tested for the identification of the medicinal plants and their parts. The prototype system has been implemented. Results of the experiments prove the effectiveness and superiority of this method.