论文部分内容阅读
本试验按主成分分析原理,使用自编的计算机程序,对MSS数据图象进行了主成分变换。通过对变换所得结果的分析表明:第一、第二两个主成分包含了原MSS图象的绝大部分信息。对于进行土地利用分类研究只需应用该两个主成分信息即可,但又不可仅取其中之一。在主成分分析中,以主成分方差和≥85％来取舍主成分的方法,在此是不适宜的。应用主成分分析技术能有效地减少数据量,节省时耗,而且会更有助于人们对数据信息进行分析研究。它确是一项理想灼信息提取与数据压缩技术。
According to the principle of principal component analysis, this experiment uses the self-compiled computer program to transform the principal component of MSS data image. The analysis of the results of the transformation shows that the first and second principal components contain most of the information of the original MSS image. For the study of land use classification, we only need to apply the two principal components information, but we can not only take one of them. In the principal component analysis, the principal component variance and ≥ 85% to choose the principal component method, this is not appropriate. Application of principal component analysis technology can effectively reduce the amount of data, save time and money, and will be more helpful for people to analyze the data and information. It is indeed a powerful technology for information extraction and data compression.