基于低秩稀疏图的结构保持投影算法  

Structure preserving projection algorithm based on low rank and sparse graph

作　　者：杨国亮[1] 罗璐[1] 丰义琴 梁礼明[1] 

机构地区：[1]江西理工大学电气工程与自动化学院,江西赣州341000

出　　处：《计算机工程与科学》2015年第8期1584-1590,共7页Computer Engineering & Science

基　　金：国家自然科学基金资助项目(51365017;61305019);江西省科技厅青年科学基金资助项目(20132bab211032)

摘　　要：在图嵌入理论框架下,能够较好地揭示数据本质特性的图在一些维数约简方法中起到关键性的作用。基于稀疏表示和低秩表示方法,构建了一种低秩稀疏图,能够同时揭示数据的局部结构信息和全局结构信息。然后,利用图嵌入理论方法使这些特性在线性投影的过程中得以保持不变,从而学习出高维数据有效的低维嵌入。在标准的人脸和手写数字数据集(ORL,Yale,PIE,MNIST)上进行实验,同传统的图嵌入方法比较,结果表明了算法的有效性。In the unifying frameworks like graph embedding, constructing a good graph to represent data properties is critical for dimensionality reduction technology. In this paper, we construct a low rank and sparse graph to reveal local and global structure information of the data based on sparse representation and low rank representation. We first use graph embedding technology to preserve such properties during the linear projections, and then obtain the low-dimensional embedding of the original high-dimensional data. The effectiveness of the proposed method is compared with the state-of-the-art algorithms and is verified on face and handwritten digit databases （ORL,Yale,PIE,MNIST）.

关 键 词：图嵌入 稀疏表示 低秩表示 低秩稀疏图 线性投影 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]