An Analysis of Segmentation Techniques to Identify Herbal Leaves from Complex Background

Abstract

Herbal leaves are used widely in local medication. But now a day, an ordinary person has little knowledge about those herbs and he may not identify such herbals easily. As a first step of computer based recognition of herbs, an analysis has been made to identify the best method for segmenting leaves object from its background. This type of segmentation is a preprocessing step required in identification of species of leaves or plants. Several methods are available for detecting the objects based on global and local features of an image. In this paper we are examining various object detection techniques for segmenting leaves based on color, shape and texture. Features like local adaptive mean color, evidence based color model, color histogram techniques are used. Boundary structure model is used to detect the leaves based on boundary descriptors of an image and Chan-Vese algorithm is used to segment the leaves from complex background. To extract leaves from texture background, edge focusing algorithm is used. From our experimentation analysis, shape is the powerful characteristics of segmenting leaf images and Chan-Vese algorithm provides better results compared to other techniques without affecting the leaf colors, texture etc.