2DPCA在遥感图像压缩中的应用  

THE APPLICATION OF 2D PCA TO THE REMOTE SENSING IMAGE COMPRESSION

作　　者：吴学明[1] 杨武年[1] 李灿平[2] 

机构地区：[1]成都理工大学国土资源信息技术与应用国土资源部重点实验室,四川成都610059 [2]成都理工大学信息工程学院,四川成都610059

出　　处：《物探化探计算技术》2008年第4期340-344,266,共5页Computing Techniques For Geophysical and Geochemical Exploration

摘　　要：Two Dimensional Principal Analysis是新近提出的一种图像分析方法,并已在特征提取与人脸和物体识别中得到较好应用。由于2DPCA本身就具有数据压缩功能,在用于去除图像的空间相关性中,可实现对数据的压缩,尤其是对高光谱或多光谱遥感图像的压缩。实验结果表明,这类方法不仅有效,而且压缩性能良好。PCA (Principal Component Analysis) is, due to its perfect performance, regarded as an optimal data compression technique. 2D PCA (Two-dimensional Principal Component Analysis) is a newly proposed approach for image analysis, which is well applied in feature extraction, face recognition and object recognition. Because of its function on data compression, 2D PCA is used to decorrelate on spatial information in images, consequently to compress data, especially the multi-spectral image and haperspectral image data. The experimental results show the validity and the good performance of this newly proposed method.

关 键 词：图像压缩 高光谱 PCA 2DPCA 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]