基于模糊支持向量机的超光谱遥感图像分类

Hyperspectral image classification based on fuzzy support vector machine

支持向量机(SVM)应用到超光谱图像分类中有较好的识别效果,但它在解决多分类问题时,存在不可分区域的局限性.为此提出了一种基于一对一SVM的模糊支持向量机,并将该方法应用到超光谱图像分类实验,结果表明该方法不仅改善了不可分区域的存在问题,而且比传统的SVM在分类精度上有明显的提高.

Support Vector Machine （SVM） has a good identification effect in HSI classification. However, the unclassifiable regions often exist in SVM-based classification with multi-classes included. Under this condition, this paper proposes an FSVM technique based on 1-a-1 SVM, and applies it to HSI classification. The results show that it not only reduces the existence of unclassifiable regions, but also gets better classification accuracy than the traditional SVM.