期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2008
卷号：8
期号：9
页码：224-228
出版社：International Journal of Computer Science and Network Security
摘要：This paper introduces a novel approach to supervised classification of multispectral images. The approach uses a new discriminative training algorithm for discrete hidden Markov tree (HMT) generative models applied to the multi-resolution ranklet transforms. System is implemented and tested on a set of Landsat 7-band images containing eight different land cover classes. Experimental results of the system show significant improvement over the baseline HMT system and give a superior performance in land cover classification.
关键词：HMT; SVM; land cover classification; discriminative training.
Loading...
