基于PCA的高光谱遥感图像分类

高光谱遥感图像的出现进一步提升遥感图像分类的准确性,但高光谱遥感图像的数据量大,处理高光谱遥感图像复杂度高、效率低。为解决这一问题,将主成分分析算法作为遥感图像分类的预处理技术。分析主成分分析算法的原理,利用主成分分析算法提取高光谱图像的主要波段图像。通过实验验证得出结论:高光谱遥感图像的主波段图像包含分类所需的大部分信息,利用少数的主波段图像即可达到70%以上的分类正确率。实验结果表明,在保证分类正确率的前提下,PCA算法可有效地减少图像分类处理的数据量,提高图像的处理效率。

Principal component analysis for hyper spectral image classification

The availability of hyper spectral images enhances the accuracy of remote sensing image classification,but the problem is the high time complexity and low execution efficiency w hen processing the hyper spectral image,because of the huge data of hyper spectral image.In order to solve the problems, this w ork uses the principal component analysis algorithm as the preprocessing technique for the classification of hyper spectral images. First, the principle of principal component analysis algorithm is analyzed.Second,the principal component analysis algorithm is used to extract the principal component image bands of hyper spectral images.A brief presentation of the principal component analysis approach is followed by an examination,which reveals that the principal component image bands contain significant information.The use of the first few principal component images can yield about 70 percent correct classification rate. This study suggests that with the premise of ensuring classification accuracy, the amount of data for the classification of hyper spectral images can be reduced effectively and the execution efficiency can be improved.