基于直接局部保持投影和尺度不变特征变换的人脸识别方法

doi:10.3724/SP.J.1087.2012.02588

计算机应用 ›› 2012, Vol. 32 ›› Issue (09): 2588-2591.DOI: 10.3724/SP.J.1087.2012.02588

基于直接局部保持投影和尺度不变特征变换的人脸识别方法

李政仪^1,2*,冯贵玉³,赵龙²

1.长沙民政职业技术学院软件学院,长沙 410004;
2.国防科学技术大学计算机学院,长沙 410073;
3.北京图形研究所,北京 100029

收稿日期:2012-03-05 修回日期:2012-05-07 发布日期:2012-09-01 出版日期:2012-09-01
通讯作者: 李政仪
作者简介:李政仪(1979-),女,湖南石门人,讲师,硕士,主要研究方向:模式识别、人机交互; 冯贵玉(1979-),男,山东滕州人,工程师,博士,主要研究方向:模式识别; 赵龙(1959-),男,江苏扬州人,教授,主要研究方向:计算机仿真、分布式战场。
基金资助:
国家自然基金资助项目(61005084);教育部高等教育博士点基金资助项目(20114307120032);湖南省教育厅科技项目(11C0076)

Face recognition method based on DLPP-SIFT

LI Zheng-yi^1,2*,FENG Gui-yu³,ZHAO Long²

1.School of Software,Changsha Social Work College,Changsha Hunan 410004,China;
2.College of Computer,National University of Defense Technology,Changsha Hunan 410073,China;
3.Beijing Graphics Research Institute,Beijing 100029,China

Received:2012-03-05 Revised:2012-05-07 Online:2012-09-01 Published:2012-09-01

摘要/Abstract

摘要： 尺度不变特征变换(SIFT)算法提取的人脸特征具有一定的鲁棒性,但存在数据维数过高和计算过于复杂的问题。为此,提出一种基于直接局部保持投影—尺度不变特征变换(DLPP-SIFT)的人脸识别算法。首先采用SIFT算法进行特征提取,然后结合子空间方法局部保持投影(LPP)进行降维,利用直接对角化方法求取特征矩阵,解决了LPP的奇异值问题。在ORL和FERET人脸库的实验结果表明,DLPP-SIFT算法可显著减少计算复杂度和特征匹配时间,与SIFT、主成分分析(PCA)-SIFT、LPP-SIFT相比,具有更好的鲁棒性。

关键词: 人脸识别, 子空间, 局部保持投影, 尺度不变特征变换

Abstract: The Scale Invariant Feature Transform (SIFT) algorithm is robust to the feature extraction of face image. However, the feature data derived by SIFT is of high dimension, and is difficult to be handled. Therefore, a Direct Locality Preserving Projections-SIFT (DLPP-SIFT) algorithm was proposed. In the algorithm, SIFT was used to extract feature, and the subspace method with Locality Preserving Projections (LPP) was utilized for dimension reduction. This algorithm solved locality preserving problem via simultaneous diagonalization; therefore, the singularity of the matrix was avoided. The experiments on ORL and FERET face databases show that the proposed algorithm reduces the computation complexity and matching time of features successfully, and is more robust than SIFT, Principal Component Analysis (PCA)-SIFT and LPP-SIFT methods.

Key words: face recognition, subspace, Locality Preserving Projection (LPP), Scale Invariant Feature Transform (SIFT)

中图分类号:

TP391.4

李政仪冯贵玉赵龙. 基于直接局部保持投影和尺度不变特征变换的人脸识别方法[J]. 计算机应用, 2012, 32(09): 2588-2591.

LI Zheng-yi,FENG Gui-yu,ZHAO Long. Face recognition method based on DLPP-SIFT[J]. Journal of Computer Applications, 2012, 32(09): 2588-2591.

参考文献

[1]WANG Y,WU Y.Face recognition using intrinsic faces [J].Pattern Recognition,2010,43(10):3580-3590.
[2]HWANG W,WANG H,KIM H,et al.Face recognition system using multiple face model of hybrid Fourier feature under uncontrolled illumination variation [J].IEEE Transactions on Image Processing,2011,20(4):1152-1165.
[3]CHOWDHURY S,SING J K,BASU D K,et al.Feature extraction by fusing local and global discriminant features:An application to face recognition [C]// ICCIC 2010:Proceedings of IEEE International Conference on Computational Intelligence and Computing Research.Piscataway,NJ:IEEE Press,2010:519-522.
[4]KRIZAJ J,STRUC V,PAVESIC N.Adaptation of SIFT features for robust face recognition [C]// ICIAR '10:Proceedings of the 7th International Conference on Image Analysis and Recognition.Berlin:Springer-Verlag,2010:394-404.
[5]LOWE D.Distinctive image features from scale-invariant key points [J].International Journal of Computer Vision,2004,60(2):91-110.
[6]KRIZAJ J,STRUC V,PAVESIC,N.Adaptation of SIFT features for face recognition under varying illumination [C]// MIPRO 2010:Proceedings of the 33rd International Convention.Piscataway,NJ:IEEE Press,2010:691-694.
[7]HUANG F C,HUANG S Y,KER J W,et al.High-performance SIFT hardware accelerator for real-time image feature extraction [J].IEEE Transactions on Circuits and Systems for Video Technology,2012,22(3):340-351.
[8]YAN K,RAHUL S.PCA-SIFT:A more distinctive representation for local image descriptors [C]// CVPR 2004:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2004:II506-II513.
[9]STEFAN Z,ALEXEI E.Detection of multiple deformable objects using PCA-SIFT [C]// AAAI-07/IAAI-07:Proceedings of National Conference on Artificial Intelligence.New York:AAAI Press,2007:1127-1132.
[10]KARTHEEK M,JAYNTHI S.Local descriptor based on texture of projections [C]// ICVGIP 2010:Proceedings of the 7th Indian Conference on Computer Vision,Graphics and Image Processing.New York:ACM Press,2010:398-404.
[11]徐小明,杨丹,张小洪,等.基于局部不变映射的特征描述器算法[J].自动化学报,2008,34(9):1174-1177.
[12]冯贵玉.人脸与掌纹识别的子空间特征提取方法研究[D].长沙:国防科学技术大学,2007.
[13]陆文佳.基于PCA-SIFT算法的人脸识别技术的研究[D].武汉:武汉理工大学,2011.
[14]LI D,TANG X,WITOLD P.Face recognition using decimated redundant discrete wavelet transforms [J].Machine Vision and Applications,2012,23(2):391-401.
[15]YANG D,ANDRZEJ S.Performance evaluation of low-dimensional SIFTs [C]// ICIP 2010:Proceedings of 2010 IEEE International Conference on Image Processing.Piscataway,NJ:IEEE Press,2010:2729-2732.

基于直接局部保持投影和尺度不变特征变换的人脸识别方法

Face recognition method based on DLPP-SIFT

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	高工, 杨红雨, 刘洪. 基于深度学习的三维点云人脸识别[J]. 计算机应用, 2021, 41(9): 2736-2740.
[2]	谢雨, 蒋瑜, 龙超奇. 基于随机子空间的扩展隔离林算法[J]. 计算机应用, 2021, 41(6): 1679-1685.
[3]	林筠超, 万源. 基于图结构优化的自适应多度量非监督特征选择方法[J]. 计算机应用, 2021, 41(5): 1282-1289.
[4]	李虹霞, 秦品乐, 闫寒梅, 曾建潮, 鲍骞月, 柴锐. 基于面部特征图对称的人脸正面化生成对抗网络算法[J]. 计算机应用, 2021, 41(3): 714-720.
[5]	吕佳, 鲜焱. 结合改进密度峰值聚类和共享子空间的协同训练算法[J]. 计算机应用, 2021, 41(3): 686-693.
[6]	胡立华, 左威健, 聂瑶瑶. 基于加权相似性度量的特征匹配方法[J]. 计算机应用, 2021, 41(2): 511-516.
[7]	朱玉娜, 张玉涛, 闫少阁, 范钰丹, 陈韩托. 基于半监督子空间聚类的协议识别方法[J]. 计算机应用, 2021, 41(10): 2900-2904.
[8]	王丽娟, 陈少敏, 尹明, 许跃颖, 郝志峰, 蔡瑞初, 温雯. 基于近邻图改进的块对角子空间聚类算法[J]. 计算机应用, 2021, 41(1): 36-42.
[9]	方书雅, 刘守印. 基于学生人体检测的无感知课堂考勤方法[J]. 计算机应用, 2020, 40(9): 2519-2524.
[10]	黄学雨, 徐浩特, 陶剑文. 具有特征选择的多源自适应分类框架[J]. 计算机应用, 2020, 40(9): 2499-2506.
[11]	赵青, 余元辉. 基于分层特征化网络的三维人脸识别[J]. 计算机应用, 2020, 40(9): 2514-2518.
[12]	李杏峰, 黄玉清, 任珍文. 联合低秩稀疏的多核子空间聚类算法[J]. 计算机应用, 2020, 40(6): 1648-1653.
[13]	李东博, 黄铝文. 重加权稀疏主成分分析算法及其在人脸识别中的应用[J]. 计算机应用, 2020, 40(3): 717-722.
[14]	龚锐, 丁胜, 章超华, 苏浩. 基于深度学习的轻量级和多姿态人脸识别方法[J]. 计算机应用, 2020, 40(3): 704-709.
[15]	程玉胜, 宋帆, 王一宾, 钱坤. 基于专家特征的条件互信息多标记特征选择算法[J]. 计算机应用, 2020, 40(2): 503-509.