一种新的基于最大边缘准则的监督流形学习方法  

New Supervised Manifold Learning Method Based on MMC

作　　者：袁暋[1] 杨瑞国[2] 原媛[2] 雷迎科[2] 

机构地区：[1]合肥学院网络与智能信息处理重点实验室,合肥230022 [2]电子工程学院,合肥230037

出　　处：《计算机科学》2014年第4期273-279,301,共8页Computer Science

基　　金：国家自然科学基金(61272333;61273302;61005010);安徽省自然科学基金(1208085MF94;1208085MF98;1308085MF84)资助

摘　　要：在深入研究局部样条嵌入算法(LSE)的基础上,引入明确的线性映射关系,构建平移缩放模型和正交化特征子空间,提出了一种正交局部样条判别投影算法(O-LSDP),有效解决了原始LSE算法存在的两个主要问题:样本外点学习问题和无监督模式学习问题。该算法能够应用于模式分类问题并显著改善算法的分类识别能力。在标准人脸数据库上进行的实验比较分析验证了该算法的有效性与可行性。Based on the analysis of local spline embedding （LSE） method,we proposed an efficient feature extraction algorithm called orthogonal local spline discriminant projection （O-LSDP）.By introducing an explicit linear mapping,constructing different translation and rescaling models for different classes as well as orthogonalizing feature subspace,OLSDP can effectively circumvent the two major shortcomings of the original LSE algorithm,i.e.,out-of-sample and unsupervised learning.O-LSDP not only inherits the advantages of LSE which uses local tangent space as a representation of the local geometry so as to preserve the local structure,but also makes full use of class information and orthogonal subspace to significantly improve discriminant power.Extensive experiments on standard face databases and plant leaf data set verify the feasibility and effectiveness of the proposed algorithm.

关 键 词：特征提取 子空间学习 局部样条嵌入 最大边缘准则 流形学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]