摘要
该文分析了试验区内的建筑、耕地、园地、林地、水体等 5种典型地物灰度的概率分布特点 ,结果表明这 5种地物的灰度概率分布并非标准的正态分布 ,而是近似的正态分布。通过对训练样本进行高斯正态化处理 ,即用高斯正态函数修正训练样本的数据 ,使参与分类训练样本的灰度概率分布成为标准的正态分布 ,进而修正类条件概率密度函数 ,尔后用最大似然法进行分类 ,结果使分类精度提高 5 .2 5 %。
This paper analyzed the probability distribution of pixel gray of the following 5 kinds of objects such as building, farmland, garden plot, woodland and water. The results showed that the probability distributsion of pixel gray of the 5 kinds of objects was not standard normal distribution, but approximately normal distribution. This paper revised the training samples with Gaussian normal function, the probability distribution of pixel gray of the revised training sample was standard normal distribution. So condition probability density function of class was modified, the classification accuracy for maximum likelihood algorithm increased by 5.25%.
出处
《农业工程学报》
EI
CAS
CSCD
北大核心
2003年第4期54-57,共4页
Transactions of the Chinese Society of Agricultural Engineering
关键词
最大似然法
概率分布
高斯正态函数
maximum likelihood algorithm
probability distribution
Gaussian normal function
