基于小样本条件下线性判别分析图像增强算法研究  

A New Dimensionality Reduction Method for Small Sample Size Problem

作　　者：陈平[1] 廖玉霞[2] 

机构地区：[1]重庆电子工程职业学院,培训与继续教育学院,重庆401331 [2]重庆电子工程职业学院通识教育学院,重庆401331

出　　处：《科学技术与工程》2013年第6期1653-1656,共4页Science Technology and Engineering

基　　金：重庆市自然科学基金项目(cstc2012jjA40022)资助

摘　　要：针对以往降维处理方法在小样本条件下受到矩阵奇异化的限制,从而无法进行有效的奇异值分解以及逆变换的缺陷,提出了一种自动对变换矩阵添加扰动量,从而保证奇异值分解和逆变换顺利进行的算法。首先,定义了线性变换矩阵的构成模式,利用线性投影变换将样本点投影到null空间和幅度空间;然后在压缩后的幅度空间对变换矩阵自动添加扰动量,在此基础上进行奇异值分解和逆变换,从而计算得到最终的从高维空间到低维空间的线性变换矩阵。无需认为设定扰动量,能自动实现投影变换的计算。能广泛使用在高维特征空间的降维处理,尤其是少样本条件下的高维特征空间降维处理中。Dimensionality reduction is a big problem for pattern recognition, especially for small sample size. The normal LDA approach suffers plenty of problems for dimensionality reduction because it the singularity problem for data set. And the pseudoinverse method also has drawbacks because of the inverse is not always possible for dataset. A method is proposed which add perturbation into the matrix automatically and makes the inverse of the ma trix is always possible. The experiment results show that the proposed method provide reliable performance for di mension reduction for recognition tasks.

关 键 词：图像增强 高斯模型 降维 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]