Author(s)

Dong An

Corresponding Author

Dong An

Abstract

With the progress of science and technology, the image data is increasing rapidly, including network image, video, etc.. How to manage a large number of image data effectively is a challenge for researchers. Image clustering algorithm is used to manage the image data and classify data information. In this paper, we propose an image clustering algorithm based on support vector machine and hidden markov model. Markov model can establish the mathematical relationship between image pixels in different layers, and we can predict the clustering result and the clustering center. Support vector machine is a new kind of machine learning algorithm based on statistical learning theory, which can find the optimal classification hyperplane in high dimensional feature space through optimum solution. Based on the basic theory of support vector machine, a remote sensing image classifier based on support vector machine is established. Experimental results show that the accuracy of image classification using svm is obviously superior than that neural network based algorithm and maximum likelihood algorithm.

Keywords

Support Vector Machine; Hidden Markov Model; Image Clustering Algorithm; Random Field