基于不同分块多特征优化融合的人脸识别研究

doi:10.12068/j.issn.1005-3026.2017.03.002

东北大学学报:自然科学版 ›› 2017, Vol. 38 ›› Issue (3): 310-314.DOI: 10.12068/j.issn.1005-3026.2017.03.002

基于不同分块多特征优化融合的人脸识别研究

贾明兴¹，杜俊强¹，宋鹏飞¹，田澍²

(1. 东北大学信息科学与工程学院，辽宁沈阳110819； 2. 东北大学软件学院，辽宁沈阳110169)

收稿日期:2015-10-12 修回日期:2015-10-12 出版日期:2017-03-15 发布日期:2017-03-24
通讯作者: 贾明兴
作者简介:贾明兴(1972-)，男，辽宁凌源人，东北大学教授.
基金资助:
国家科技支撑计划项目(2013BAK02B01); 辽宁省科技计划项目(2013231025).

Face Recognition Based on Multi-feature Optimization Fusion of LBP， LPQ and Gabor with Multi-scale Blocks

JIA Ming-xing¹， DU Jun-qiang¹， SONG Peng-fei¹， TIAN Shu²

1. School of Information Science & Engineering， Northeastern University， Shenyang 110819， China; 2. School of Software， Northeastern University， Shenyang 110169， China.

Received:2015-10-12 Revised:2015-10-12 Online:2017-03-15 Published:2017-03-24
Contact: JIA Ming-xing
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对光照、姿态、表情等复杂情形下人脸识别率较低的问题，提出基于不同分块多特征优化融合的人脸识别方法.首先考虑了局部二值模式、局部相位量化特征和小波变换特征.进一步，考虑单一分块算法会使分割线周边信息不能完整提取，从而丢失对人脸识别的有用特征，提出了人脸灰度图像多重分块的方法.最后，采用遗传算法对不同分块多特征进行权值寻优，得到最优权值.在大规模人脸数据集FRGC2.0数据库上进行实验四验证，验证率达到95.31%(FAR0.1%)，首选识别率为99.06%，相比于前期文献，该算法能多方位提取人脸特征信息，提高人脸识别率，且所用特征较少.

关键词: LBP, LPQ, Gabor, 最优权值, 多重分块, 人脸识别

Abstract: There is still a problem of low recognition rate in face recognition when dealing with complex situations such as illumination， pose and facial expression， so a face recognition method based on multi-feature optimization fusion with multi-scale blocks was proposed. Three complementary characters were considered as the features needed， such as local binary pattern(LBP)， the local phase quantization(LPQ) and wavelet transform. Further， a method of multi-scale blocks of face grayscale image was proposed to consider that the single block algorithm made the surrounding information not be fully extracted and thereby lost useful features for face recognition. Finally， genetic algorithm was used to optimize the weights of multi-feature of multi-scale blocks， and the optimal weights could be obtained. Experiment 4 with this method was tested on the basis of large scale face data set FRGC2.0 database， and the validation rate of the method reached 95.31%， with recognition rate reaching 99.06%. Compared to the previous literature， this algorithm can extract more feature information of human face， and improve the face recognition rate.

Key words: LBP(local binary pattern), LPQ(local phase quantization), Gabor, optimal weight, multi-scale blocks, face recognition

中图分类号:

TP391.4

贾明兴，杜俊强，宋鹏飞，田澍. 基于不同分块多特征优化融合的人脸识别研究[J]. 东北大学学报:自然科学版, 2017, 38(3): 310-314.

JIA Ming-xing， DU Jun-qiang， SONG Peng-fei， TIAN Shu. Face Recognition Based on Multi-feature Optimization Fusion of LBP， LPQ and Gabor with Multi-scale Blocks[J]. Journal of Northeastern University Natural Science, 2017, 38(3): 310-314.

参考文献

[1]Huang D，Shan C，Ardabilian M，et al.Local binary patterns and its application to facial image analysis:a survey［J］.IEEE Transactions on Systems Man & Cybernetics Part C，2011，41(6):765-781.
[2]张洁玉，赵鸿萍，陈曙.自适应阈值及加权局部二值模式的人脸识别［J］.电子与信息学报，2014(6):1327-1333.(Zhang Jie-yu，Zhao Hong-ping，Chen Shu.Face recognition based on weighted local binary pattern with adaptive threshold［J］.Journal of Electronics & Information Technology，2014(6):1327-1333.)
[3]Ojansivu V，Heikkil J.Blur insensitive texture classification using local phase quantization［C］// Image and Signal Processing，International Conference.Cherbourg-Octeville，2008:236-243.
[4]Zhang W，Shan S，Qing L，et al.Are Gabor phases really useless for face recognition?［J］.Formal Pattern Analysis & Applications，2009，12(3):301-307.
[5]Su Y，Shan S，Chen X，et al.Hierarchical ensemble of global and local classifiers for face recognition［J］. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society，2009，18(8):1885-1896.
[6]Pu X，Wang Y.Face detection on partial and holistic LBP features［C］// International Conference on Electrical and Control Engineering.Yichang，2011:1071-1074.
[7]Wei W，Huang F F，Li J W，et al.Face description and recognition using multi-scale LBP feature［J］.Optics & Precision Engineering，2008，16(4):696-705.
[8]Hwang W，Park G，Lee J，et al.Multiple face model of hybrid fourier feature for large face image set［C］// IEEE Computer Society Conference on Computer Vision & Pattern Recognition.New York，2006:1574-1581.
[9]Zhang W，Shan S，Gao W，et al.Local Gabor binary pattern histogram sequence (LGBPHS):a novel non-statistical model for face representation and recognition［C］// Tenth IEEE International Conference on Computer Vision.Beijing:IEEE Computer Society，2005:786-791.
[10]Xie S，Shan S，Chen X，et al.Fusing local patterns of Gabor magnitude and phase for face recognition［J］.IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society，2010，19(5):1349-1361.
[11]殷飞，焦李成，杨淑媛.基于子空间类标传播和正则判别分析的单标记图像人脸识别［J］.电子与信息学报，2014(3):610-616.(Yin Fei，Jiao Li-cheng，Yang Shu-yuan.Subspace label propagation and regularized discriminant analysis based single labeled image person face recognition［J］. Journal of Electronics & Information Technology，2014(3):610-616.)
[12]曹明明，干宗良，崔子冠，等.基于2D-PCA特征描述的非负权重邻域嵌入人脸超分辨率重建算法［J］.电子与信息学报，2015(4):777-783.(Cao Ming-ming，Gan Zong-liang，Cui Zi-guan，et al.Novel neighbor embedding face hallucination based on non-negative weights and 2D-PCA feature［J］.Journal of Electronics & Information Technology，2015(4):777-783.)
[13]Zhao C，Gao F.A nested-loop fisher discriminant analysis algorithm［J］.Chemometrics & Intelligent Laboratory Systems，2015，146:396-406.
[14]Shan S，Zhang W，Su Y，et al.Ensemble of piecewise FDA based on spatial histograms of local (Gabor) binary patterns for face recognition［C］// IEEE Computer Society.Washington，2006:606-609.
[15]Deng W，Hu J，Guo J，et al.Emulating biological strategies for uncontrolled face recognition［J］.Pattern Recognition，2010，43(6):2210-2223.
[16]Li Y，Shan S，Zhang H，et al.Fusing magnitude and phase features for robust face recognition［C］// Asian Conference on Computer Vision.Daejeon，2012:601-612.
[17]Li H，Hua G，Shen X，et al.Eigen-PEP for video face recognition［C］// Computer Vision-ACCV 2014.Singapore:Springer International Publishing，2014:17-33.
[18]Zhu Z，Luo P，Wang X，et al.Recover canonical-view faces in the wild with deep neural networks［J］.Technical Report Arxiv，2014:1404.3543.
[19]Yi D，Lei Z，Li S Z.Shared representation learning for heterogenous face recognition［C］// IEEE International Conference and Workshops on Automatic Face and Gesture Recognition.Washington:IEEE，2015:1-7.
[20]Ding C，Choi J，Tao D，et al.Multi-directional multi-level dual-cross patterns for robust face recognition［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence，2016，38(3):518-531.

基于不同分块多特征优化融合的人脸识别研究

Face Recognition Based on Multi-feature Optimization Fusion of LBP， LPQ and Gabor with Multi-scale Blocks

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

编辑推荐

Metrics

本文评价

[1]	张祥德，朱和贵，李倩颖，唐青松. 基于MBC和POEM特征的人脸识别方法[J]. 东北大学学报:自然科学版, 2015, 36(11): 1526-1529.
[2]	李根，李文辉. 基于混合蛙跳算法的长时间跨度人脸识别[J]. 东北大学学报:自然科学版, 2014, 35(7): 955-959.
[3]	崔兆华，张萍，李洪军，高立群. 融合结构特征的增强型FCM图像分割算法[J]. 东北大学学报(自然科学版), 2013, 34(7): 922-925.
[4]	张祥德;黎明奇;王琪;孙艳蕊;. 基于多方向Gabor滤波器和Adaboost的虹膜识别方法[J]. 东北大学学报(自然科学版), 2012, 33(1): 39-42.
[5]	依玉峰;高立群;程伟;于鸿银;. 自适应随机游走图像分割算法[J]. 东北大学学报(自然科学版), 2011, 32(8): 1092-1096.
[6]	王琪;张祥德;印雨;张铁;. 基于椭圆拟合的晃动虹膜图像的检测算法[J]. 东北大学学报(自然科学版), 2010, 31(7): 938-941.
[7]	丛家慧;颜云辉;董德威;. Gabor滤波器在带钢表面缺陷检测中的应用[J]. 东北大学学报(自然科学版), 2010, 31(2): 257-260.
[8]	张祥德;唐青松;陆小军;朱和贵;. 基于神经网络和人脸特征的密钥管理方法[J]. 东北大学学报(自然科学版), 2009, 30(6): 817-820.
[9]	王晓哲;李晨阳;吴成东;. 基于快速小波变换和FLD的人脸识别算法[J]. 东北大学学报(自然科学版), 2009, 30(2): 166-168+183.
[10]	毛克明;王国仁;于长永;金艳;. 一种改进的基于Gabor小波的指纹增强算法[J]. 东北大学学报(自然科学版), 2009, 30(1): 46-49.
[11]	赵丽红;孙宇舸;蔡玉;徐心和;. 基于核主成分分析的人脸识别[J]. 东北大学学报(自然科学版), 2006, 27(8): 847-850.
[12]	苏羽;赵海;王刚;苏威积. 一种基于BP算法的融合神经网络[J]. 东北大学学报(自然科学版), 2003, 24(11): 1037-1040.