Plant Identification from Leaf Using Artificial Neural Network

Abstract

In the world, some useful and important species of plants are going extinct day by day. To control the phenomena, steps are identification, restoring and protecting of the plants. Recognizing plants is a vital problem especially for biologists, chemists, and environmentalists. Plant recognition can be performed by human experts manually but it is a time consuming and lowefficiency process. Automation of plant recognition is an important process for the fields working with plants. This paper presents an approach for plant recognition using leaf images. Identifying plants using key components i.e. leafs to protect medicinal plants. Extraction of shape, color, and texture features from leaf images. Training an artificial neural network (ANN) classifier to identify the exact leaf class. Key issue lies in selection of proper image input features to attain high efficiency with less computational complexity. This work is implemented using the image processing and neural network toolboxes in MATLAB. The presented approach is tested on 100 leaf images which are 10 kinds of leaves.
Edge detection is one of the fundamental tool in image processing, machine vision and computer vision, which aim at identifying points in a digital image. It is an important tool for medical image segmentation.