论文部分内容阅读
支持向量机(SVM)是根据统计学习理论提出的新的研究方法,它在解决小样本、非线性及高维模式识别问题中表现出了许多特有的优势,在模式识别、函数逼近和概率密度估计等方面取得了良好的效果。由于高光谱图像波段数目多,各波段间具有较强的相关性,因此通过主成分分析(PCA)方法对高光谱数据进行预处理,达到了降维的目的,同时也去除了噪声波段。用支持向量机方法对高光谱遥感图像进行分类,可实现图像的分类识别。
Support Vector Machine (SVM) is a new research method based on statistical learning theory. It shows many unique advantages in solving small sample, nonlinear and high-dimensional pattern recognition problems. Pattern recognition, function approximation and probability density Estimation and other aspects have achieved good results. Due to the high number of hyperspectral image bands and the strong correlation between the bands, the principal component analysis (PCA) method is used to pre-process the hyperspectral data, which achieves the purpose of dimensionality reduction and removes the noise band. Using support vector machine method to classify hyperspectral remote sensing images can realize the classification and recognition of images.