Leaf recognition algorithm using support vector machine with Hu moments and local binary patterns

Abstract

Leaf recognition is convenient for plant classification and it is an important subfield of pattern recognition. Different leaf features such as color, shape and texture are used as well as different classifiers including artificial neural networks, k-nearest neighbor and support vector machines. In this paper we propose an algorithm based on tuned support vector machine as a classifier and Hu moments and uniform local binary pattern histogram parameters as features. Our proposed algorithm was tested on leaf images from standard benchmark database and compared with other approaches from literature where it proved to be more successful (higher recognition percentage).