...和背景知识进而构造大量训练样本的问题,从特征提取的角度提出了一种用于高光谱混合像元分类的非监督约束线性判别分析算法(UCLDA)。UCLDA首先利用顶点成分分析(VCA)提取端元,然后用光谱角匹配方法(SAM)构造训练样本并基于约束线性判别分析(CLDA)进行特征提取,最...
基于6个网页-相关网页
采用LBP算法与直接线性判别分析算法相结合的人耳特征提取方法在识别率方面与原始图像特征提取方法相比有明显提升。
The algorithm based on LBP and direct linear discriminant analysis have distinct advance than the extraction algorithm using the original image in recognition rate.
拓展算法三:引入统计筛选和线性判别分析相结合的分层递阶约简算法。
Extended approach three: a hierarchical reduction approach is imported, which is based on the combination of statistical feature selection and linear discriminant analysis.
多个人脸数据库上的实验结果表明,本算法能够有效地解决线性判别分析中的小样本规模问题。
Experiments demonstrate that the proposed method can effectively solve the small sample size problem of LDA.
应用推荐