Texture image classification based on support vector machine and distance classification

Abstract

In this paper we propose a classification combination algorithms for texture image classification, which named ISD (integrated SVM and distance classification) algorithm. It combines support vector machine (SVM) and distance classification into two-layer serial classifier. SVM has been proposed as a new technique for pattern recognition in recent years. It has shown to provide better generalization performance than traditional techniques, including neural networks. However, because using quadratic programming (QP) optimization techniques, the training of SVM is time-consuming, especially when the training data set is very large. So we have two classifiers combined. Firstly, we define a rejecting coefficient and rejecting rule. According the rejecting rule, the distance classifier can classify the images and give the final results, or reject to classify the input images. The rejected images are fed into SVM for further classification. ISD algorithm can take advantages of SVM and distance classification. Furthermore, ISD algorithm can use the rejected images to train SVM, thus the training is more efficient. The experiments show that the algorithm has high efficiency and low error rate.