计算机科学 ›› 2016, Vol. 43 ›› Issue (8): 286-291.doi: 10.11896/j.issn.1002-137X.2016.08.058
梅玲玲,龚劬
MEI Ling-ling and GONG Qu
摘要: 局部保持投影(LPP)通过构造近邻图来保持样本的局部结构,在构造近邻图的过程中,LPP会遇到两个参数K和σ的选择问题。近邻图的构建对算法的识别效果起着重要的作用,因而这两个参数的选择会在很大程度上影响LPP的识别率。为了避免参数的选择对识别率造成影响,提出了一种基于改进的自适应局部保持投影的人脸识别算法。首先,构造无参数的近邻图,其能够自适应地选取样本的近邻点并确定其相应的边权。其次,由于在计算过程中出现了矩阵维数过高的问题,因此采用QR分解进行降维处理。最后,利用共轭正交化使得投影轴具有统计不相关性,以降低特征矢量间的统计相关性,提高识别率。在ORL人脸库和YALE人脸库上进行了实验,结果表明改进的算法在识别率方面整体上好于LPP算法、DLPP算法、LMMC算法。
[1] Li X W.The Method of Face Recognition Based on PCA[D].Changsha:Hunan University,2010(in Chinese) 李现伟.基于PCA的人脸识别方法[D].长沙:湖南大学,2010 [2] Li R J,Han Q L,Yang X H.New Optimization Method of PCA Face Recognition[J].Journal of Dalian Jiaotong University,2008,9(4):49-50(in Chinese) 李荣健,韩其龙,杨鑫华.改进的PCA人脸识别新算法[J].大连交通大学学报,2008,9(4):49-50 [3] Yang H Y.The Improvement of Face Recognition Algorithm[D].Tianjin:Tianjin Polytechnic University,2010(in Chinese) 杨洪燕.人脸识别算法的改进[D].天津:天津工业大学,2010 [4] Hu Y.Face Recognition Algorithms Based on Principle Component Analysis and Independent Component Analysis[D].Jilin:Jilin University,2010(in Chinese) 胡月.基于主成分分析和独立成分分析的人脸识别研究[D].吉林:吉林大学,2010 [5] Liang W L.A Research on Algorithms for Face RecognitionTechnology Based on Independent Component Analysis[D].Xi’an:Xi’an University of Science and Technology,2012(in Chinese) 梁文莉.基于独立成分分析的人脸识别算法研究[D].西安:西安科技大学,2012 [6] She X Y,Zhao Y Y,Cai Y Q.Face recognition based on dynamically determining neighborhood parameter of locally linear embedding algorithm[J].Application Research of Computers,2014,31(12):3870-3872,4(in Chinese) 厍向阳,赵元元,蔡院强.基于邻域参数动态变化的局部线性嵌入人脸识别[J].计算机应用研究,2014,31(12):3870-3872,4 [7] Belkin M,Niyogi P.Laplacian eigenmaps for dimensionality reduction and data representation[J].Neural Comput,2003,5(6):1373-1396 [8] Tenenbaum J B,Silva V,Langford J C.A global geometricframework for nonlinear dimensionality reduction[J].Science,2000,0:2319-2323 [9] He Xiao-fei,Yan Shui-cheng,Hu Yu-xiao,et al.Face Recognition Using Laplacianfaces[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2005,7(3):328-340 [10] Guo Z J.The Application of Locality Preserving Maximum Margin Criterion In Face Recognition [J].Science & Technology Information,2010,1:496-697(in Chinese) 郭子健.局部保持最大间距准则在人脸识别中的应用[J].科技信息,2010,1:496-697 [11] Zhan Y B,Yin J P,Liu X W.Face Feature Extraction Based on Maximum Margin Criterion and Image Matrix Bidirectional Projection[J].Acta Automatica Sinica,2010,36(12):1645-1654(in Chinese) 詹宇斌,殷建平,刘新旺.基于大间距准则和双向投影的人脸识别特征提取方法[J].自动化学报,2010,36(12):1645-1654 [12] Qin C X,Ren W J,He C W,et al.Face Recognition Based on Weighted Maximum Margin Criterion[J].Computer Enginee-ring,2008,4(15):193-195(in Chinese) 秦春霞,任文杰,贺长伟,等.基于加权最大类间边缘准则的人脸识别[J].计算机工程,2008,4(15):193-195 [13] Gong Q,Tang P F.Uncorrelated Locality Preserving Projections Analysis Based on Maximum Margin Criterion [J].Acta Automatica Sinica,2013,39(9):1575-1580(in Chinese) 龚劬,唐萍峰.基于大间距准则的不相关保局投影分析[J].自动化学报,2013,39(9):1575-1580 [14] Wang Su-jing,Chen Hui-ling,Peng Xu-jun,et al.Exponential Locality Preserving Projections for Small Sample Size Problem[J].Neurocomputing,2011,74(17):3654-3662 [15] Xu Yong,Zhong Ai-ni,Yang Jian,et al.LPP solution schemes for use with face recognition[J].Pattern Recognition,2010,3:4165-4176 [16] Fadi D,Ammar A.Enhanced and parameterless Locality Preserving Projections for face recognition[J].Neurocomputing,2013,9:448-457 [17] Li H F,Jiang T,Zhang K S.Efficient and robust feature ex-traction by maximum margin criterion[J].IEEE Transactionson Neural Networks,2006,17(1):157-165 [18] Yang L P,Gong W G,Gu X H,et al.Complete Discriminant Locality Preserving Projections for Face Recognition[J].Journal of software,2010,21(6):1277-1286(in Chinese) 杨利平,龚卫国,辜小花,等.完备鉴别保局投影人脸识别算法[J].软件学报,2010,21(6):1277-1286 [19] Gong Q,Hua T T.Face Recognition Based on Improved Locality Preserving Projection[J].Journal of Computer Applications,2012,2(2):528-530,4(in Chinese) 龚劬,华桃桃.基于改进的局部保持投影算法的人脸识别[J].计算机应用,2012,2(2):528-530,4 [20] Liang Yi-xiong,Gong Wei-guo,Pan Ying-jun,et al.Face Recognition Using Uncorrelated,Weighted Linear Discriminant Analysis[J].Springer-Verlag Berlin Heidelberg,2005,7:192-198 [21] Gong Q,Ma J J.Face Recognition Based on Improved Two-dimensional Locality Preserving Projection Algorithm[J].Computer Engineering,2014,0(9):252-256(in Chinese) 龚劬,马家军.基于改进二维保局投影算法的人脸识别[J].计算机工程,2014,0(9):252-256 [22] Tang P F.Study on Face Recognition Based on Subspace Analysis and Frequency Domain Feature Extraction [D].Chongqing:Chongqing University,2013(in Chinese) 唐萍峰.基于子空间分析和频域特征提取的人脸识别研究[D].重庆:重庆大学,2013 [23] Li Y Z,Yang J Y.Novel Methods of Face Recognition Based on Non-negative Matrix Factorization[J].Journal of System Simulation,2008,20(1):111-116(in Chinese) 李勇智,杨静宇.基于非负矩阵分解新的人脸识别方法[J].系统仿真学报,2008,20(1):111-116 [24] Lu Gui-fu,Lin Zhong,Jin Zhong.Orthogonal Complete Discriminant Locality Preserving Projections for Face Recognition[J].Springer Science Business Media,LLC,2011,3:235-250 [25] Huang P,Tang Z M.Parameter-Free Locality Preserving Projections and Face Recognition[J].Pattern Recognition and Aitificial Intelligence,2013,26(9):865-871(in Chinese) 黄璞,唐振民.无参数局部保持投影及人脸识别[J].模式识别与人工智能,2013,6(9):865-871 |
No related articles found! |
|