基于联合协同表示与SVM决策融合的高光谱图像分类研究*

针对高光谱图像的分类问题进行了研究，提出一种基于联合协同表示（JCR）与支持向量机（SVM）模型的决策融合分类方法。首先采用联合协同表示模型对样本与字典进行多元素分解并分别进行相应的协同表示，自适应的学习多元素的残差权重并进行线性加权。其次用灰度共生矩阵计算出的统计特征量来训练多类SVM分类器。最后建立一种乘法融合规则将JCR与SVM相结合。在两个标准数据集上的实验结果表明该方法比其他方法具有更好的性能。

The Research of Hyperspectral Image Classification Based on joint collaborative representation and SVM Models With Decision Fusion

In view of the research of hyperspectral image (HSI) classification, we propose a method based on the joint collaborative representation (JCR) and support vector machine (SVM) models with decision fusion. Firstly, we use a JCR model to decompose the samples and dictionaries into multi elements and carry out corresponding cooperative representation respectively, which adaptively learning multi elements of residuals weights and linear weighted. Second, we extract the statistical features obtained from the gray level co-occurrence matrix to train a multiclass SVM classifier. Finally, we exploit a multiplicative fusion rule to combine the JCR and SVM models. The experimental results on two standard data sets demonstrate that this method achieves better performance than other competing ones.