Information Technology Reference
In-Depth Information
ShapeandTextureBasedPlantLeaf
Classification
Thibaut Beghin, James S. Cope, Paolo Remagnino, and Sarah Barman
Digital Imaging Research Centre, Kingston University, London, UK
{ t.beghin,j.cope,p.remagnino,s.barman } @kingston.ac.uk
Abstract. This article presents a novel method for classification of
plants using their leaves. Most plant species have unique leaves which dif-
fer from each other by characteristics such as the shape, colour, texture
and the margin. The method introduced in this study proposes to use two
of these features: the shape and the texture. The shape-based method
will extract the contour signature from every leaf and then calculate the
dissimilarities between them using the Jeffrey-divergence measure. The
orientations of edge gradients will be used to analyse the macro-texture
of the leaf. The results of these methods will then be combined using an
incremental classification algorithm.
Keywords: Plant identification; Shape-based analysis; texture-based
analysis; Sobel operator; incremental classification.
1
Introduction
The role of plants is one of the most important in the natural circle of life.
As they form the bulk of the living organisms able to convert the sun light
energy into food, they are indispensable to almost every other form of life. They
have interested humans since Greek antiquity and the efforts to classify them is,
perhaps, the most ancient activity of Science.
Since the development of a systematic classification of plants by the Swedish
botanist Carolus Linnaeus in the 18th century [9], plant classification has been
attempted in many different ways. The first person who studied the leaf features
in this purpose was L.R. Hicher in 1973.
Since then, with the dramatic development of digital image processing, ma-
chine vision and pattern recognition, numerous techniques for plant classification
using leaves have been investigated. To contribute to these techniques, this paper
proposes to develop a classification system using both shape-based and texture-
based analysis.
Section 2 introduces the dataset used in this paper, and the outlines the pre-
processing performed.
Section 3 presents the shape-based method which uses the contour signa-
tures of the leaves and calculates the dissimilarities between them using the
Jeffrey distance. This method has proven its effectiveness for leaf identification
[15,13,14,3,19].
 
Search WWH ::




Custom Search