The spectral-spatial classification of hyperspectral images based on Hidden Markov Random Field and its Expectation-Maximization
The spectral-spatial classification of hyperspectral images based on Hidden Markov Random Field and its Expectation-Maximization
复制标题
DOI：
10.1109/igarss.2013.6721358
复制
发表时间：
2013-07
期刊：
影响因子：
--
通讯作者：
Pedram Ghamisi;J. Benediktsson;M. Ulfarsson
中科院分区：
文献类型：
--
作者：
Pedram Ghamisi;J. Benediktsson;M. Ulfarsson
在这项工作中，提出了一种用于高光谱图像精确分类的新框架。新方法基于隐马尔可夫随机场及其期望最大化（HMRF-EM）和支持向量机（SVM）分类器。为了保留最终地图中的边缘，使用了 Sobel 边缘检测器。结果证实，与标准 SVM 方法相比，光谱和空间信息的结合可以显着改善结果。
In this work, a new framework for accurate classification of hyperspectral images is proposed. The new method is based on Hidden Markov Random Field and its Expectation Maximization (HMRF-EM) and Support Vector Machine (SVM) classifier. In order to preserve edges in final map, the Sobel edge detector is used. Result confirms that the combination of the spectral and spatial information can significantly improve results compared to the standard SVM method.