Support Vector Machine-based approach for Recognizing Bonsai Species using Leaf Image

Abstract

Recognition of Bonsai plant is one of the most challenging task. This is because most of the people have less knowledge about Bonsai especially for a beginner. For those who new to this field, it might be hard for them to recognize and identify the species of Bonsai because of its similarity in terms of shape, colour and etc. The incorrect identification of species, may resulting in damaging the Bonsai plant. Furthermore, different species of Bonsai may have different ways to take care of it. Therefore, the information about the Bonsai need to be accessible with the recognition of the species. As a solution, the aims of this project is to develop a system for recognising three species of Bonsai: 1) Adenium, 2) Red Japanese Maple and 3) Natal Plum by using its leaf. The project implemented a Rapid Application Development (RAD) Model as the methodology. There are four phases in RAD: 1) Planning, 2) Design, 3) Implementation and 4) Finalization. In pre-processed phase, feature extraction of the leaf is using colour moment and Gray-Level Co- occurrence Matrix (GLCM) were used for extracting the colour of the leaf. The species of Bonsai has been classified using Support Vector Machine-based approach and the system has been successfully recognize the species of Bonsai with accuracy of 98.2%.