Published Paper Details:

Ayurveda is an ancient system of medicine practiced in India. The main constituents of ayurvedic medicines are plant leaves and other parts of plants like root, bark etc. the Ayurvedic physicians themselves picked the medicinal plants and prepared the medicines for their patients. Today only a few practitioners follow this practice. Today the plants are collected by women and children from forest areas; those are not professionally trained in identifying correct medicinal plants. Manufacturing units often receive incorrect or substituted medicinal plants. Most of these units lack adequate quality control mechanisms to screen these plants. In addition to this, confusion due to variations in local name is also rampant. Some plants arrive in dried form and this make the manual identification task much more difficult. Incorrect use of medicinal plants makes the Ayurvedic medicine ineffective. It may produce unpredictable side effects also. In this situation, we have to know the ayurvedic leaf accurately. There are four steps involved. The first step is preprocessing that is by sharpening the RGB image. This is done by employing unsharp masking. This sharpening of the image improves the image appearance. Also, the edge or boundary points of an image are sharpened. The second step is Segmentation. Image segmentation is the process where image is divided into multiple parts. This is mainly employed to extract relevant information such as leaf portion from a digital image. Segmentation involves binarization. This binary image then passes through a morphological erosion and dilation process so that small imperfections like dots are removed. The third step is feature extraction like shape features, color features, texture analysis. Final step is classification. After feature extraction is completed, the values of these parameters will be stored in a temporary database as excel file. Based on these feature values, the image samples are classified into different classes and are ready to be tested for identification. The classification is done by using MLP and Decision Tree algorithm. Based on the correctly classified testing instances, accuracy is calculated as a measure of the efficiency of the algorithm.