摘要
标签传播算法(LP)是一种基于图的半监督学习算法,通过保持数据间的某些特殊结构,将部分有标签数据的标签信息迭代传递给无标签数据,直至获得全局的稳定状态.结合标签传播算法和线性鉴别分析提出一种流形结构保持的传播半监督降维算法(SDRMPP),采用流行结构上的重构权重并结合已知的部分标签信息进行标签传播,利用传播后获得的全体软标签信息构造离散度矩阵实现鉴别分析,通过求解目标函数的最优值获得特征抽取空间,从而对测试样本进行分类.在Yale和Feret两个标准人脸库上实验验证了该算法的有效性,尤其在只存有少量有标签样本的情况下,该算法仍能保持良好的分类性能.
Label propagation algorithm is a graph-based semi-supervised learning approach.It propagates the labels from the labeled data to the unlabeled data iteratively by preserving the special structure of the whole data until a global state is achieved.Combined with label propagation algorithm and linear discriminant analysis,we proposed a semi-supervised dimensionality reduction based on manifold structure preserving and label propagation（SDRMPP）.It propagates the labels by using the reconstruction weights as well as part of labeled data,the scatter matrices based on soft label learned by label propagation are constructed to perform the discriminant analysis.The feature extraction space was obtained by solving the optimization problem,and then the testing samples were classified into different classes.The experimental results on Yale and Feret face image database show that the proposed method is effective,especially when limited number of images were labeled,our method can still maintain its good classification performance.
出处
《小型微型计算机系统》
CSCD
北大核心
2012年第11期2414-2417,共4页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(60875004)资助
江苏省自然科学基金项目(BK2009184)资助
江苏省高校自然(10KJB510027
07KJB520133)资助
关键词
标签传播算法
LDA
流形学习
半监督降维
人脸识别
label propagation
linear discriminant analysis（LDA）
manifold learning
semi-supervised discriminant
face recognition
