整合原始人脸图像和其虚拟样本的人脸分类算法

doi:10.11896/j.issn.1002-137X.2015.05.059

摘要/Abstract

摘要： 人脸识别作为最具吸引力的生物识别技术之一,由于会受到不同的照明条件、面部表情、姿态和环境的影响,仍然是一个具有挑战性的任务。众所周知,一幅人脸图像是对人脸的一次采样,它不应该被看作是脸部的绝对精确表示。然而在实际应用中很难获得足够多的人脸样本。随着稀疏表示方法在图像重建问题中的成功应用,研究人员提出了一种特殊的分类方法,即基于稀疏表示的分类方法。受此启发,提出了在稀疏表示框架下的整合原始人脸图像和虚拟样本的人脸分类算法。首先,通过合成虚拟训练样本来减少面部表示的不确定性。然后,在原始训练样本和虚拟样本组成的混合样本中通过计算来消除对分类影响较小的类别和单个样本,在系数分解的过程中采用最小误差正交匹配追踪(Error-Constrained Orthogonal Matching Pursuit,OMP)方法,进而选出贡献程度大的类别样本并进行分类。实验结果表明,提出的方法不仅能获得较高的人脸识别的精度,而且还具有更低的计算复杂性。

关键词: 稀疏表示,贪婪算法,人脸识别,分类

Abstract: As one of the most attractive biometric techniques,face recognition is still a challenging task.This is mainly owing to the varying lighting,facial expression,pose,and environment.In this sense,a face image is just an observation and it should not be considered as the absolutely accurate representation of the face.However,even in a real world face recognition system,it is difficult to obtain enough samples.The great success of sparse representation in image reconstruction triggers the research on sparse representation based pattern classification.Inspired by this,a sparse representation based classification method using category elimination and greedy search strategy was proposed for face recognition.First,we reduced the uncertainty of the face representation by synthesizing the virtual training samples.We applied an error-constrained orthogonal matching pursuit algorithm to exploit an optimal representation result of training samples from the classes by eliminating the category and the specific training samples.The final remaining training samples are used to produce a best representation of the test sample and to classify it.Then,we selected useful training samples that are similar to the test sample from the set of all the original and synthesized virtual training samples.Finally,we devised a representation approach based on the selected useful training samples to perform face recognition.Experimental results on five widely used face databases demonstrate that our proposed approach can not only obtain higher face recognition accuracy,but also has a lower computational complexity than the other state-of-the-art approaches.

Key words: Sparse representation,Greedy algorithm,Face recognition,Classifications

刘梓,宋晓宁,唐振民. 整合原始人脸图像和其虚拟样本的人脸分类算法[J]. 计算机科学, 2015, 42(5): 289-294. https://doi.org/10.11896/j.issn.1002-137X.2015.05.059

LIU Zi, SONG Xiao-ning and TANG Zhen-min. Integrating Original Images and its Virtual Samples for Face Recognition[J]. Computer Science, 2015, 42(5): 289-294. https://doi.org/10.11896/j.issn.1002-137X.2015.05.059

参考文献

[1] Pishchulin L,Gass T,Dreuw P,et al.Image warping for facerecognition:From local optimality towards global optimization [J].Pattern Recognition,2012,45(9):3131-3140
[2] Kautkar S N,Atkinson G A,Smith M L.Face recognition in 2D and 2.5 D using ridgelets and photometric stereo[J].Pattern Recognition,2012,45(9):3317-3327
[3] Wang J,You J,Li Q,et al.Orthogonal discriminant vector forface recognition across pose [J].Pattern Recognition,2012,45(12):4069-4079
[4] Chen W,Er M J,Wu S.Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain [J].IEEE Transactions on Systems,Man,and Cybernetics,Part B:Cybernetics,2006,36(2):458-466
[5] Sharma A,Dubey A,Tripathi P,et al.Pose invariant virtualclassifiers from single training image using novel hybrid-eigenfaces [J].Neurocomputing,2010,73(10):1868-1880
[6] Beymer D,Poggio T.Face recognition from one example view[C]∥Proceedings of the Fifth International Conference on Computer Vision,1995.IEEE,1995:500-507
[7] Vetter T.Synthesis of novel views from a single face image [J].International Journal of Computer Vision,1998,28(2):103-116
[8] Tan X,Chen S,Zhou Z H,et al.Face recognition from a single image per person:A survey [J].Pattern Recognition,2006,39(9):1725-1745
[9] Bin T,Siwei L,Hua H.High performance face recognition system by creating virtual sample[C]∥Proceedings of the 2003 International Conference on Neural Networks and Signal Proces-sing,2003.IEEE,2003,2:972-975
[10] Jung H C,Hwang B W,Lee S W.Authenticating corrupted face image based on noise model[C]∥Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition,2004.IEEE,2004:272-277
[11] Thian N P H,Marcel S,Bengio S.Improving face authentication using virtual samples [C]∥Proceedings of the 2003 IEEE International Conference on Acoustics,Speech,and Signal Processing,2003(ICASSP’03).IEEE,2003,3:III-233-6
[12] Liu J,Chen S,Zhou Z H,et al.Single image subspace for face recognition [M]∥Analysis and Modeling of Faces and Gestures.Springer Berlin Heidelberg,2007:205-219
[13] Dahmen J,Keysers D,Ney H.Combined classification of handwritten digits using the ‘virtual test sample method’ [M]∥Multiple Classifier Systems.Springer Berlin Heidelberg,2001:109-118
[14] 孙玉宝.图像稀疏表示模型及其在图像处理反问题中的应用[D].南京:南京理工大学,2010
[15] 王振宇,秦立龙,刁俊良.基于K-SVD和稀疏表示的数字调制模式识别[J].计算机科学,2013,0(10):65-67
[16] Wright J,Ma Y,Mairal J,et al.Sparse representation for computer vision and pattern recognition [J].Proceedings of the IEEE,2010,98(6):1031-1044
[17] Wright J,Yang A Y,Ganesh A,et al.Robust face recognition via sparse representation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227
[18] Shi Y,Dai D,Liu C,et al.Sparse discriminant analysis for breast cancer biomarker identification and classification [J].Progress in Natural Science,2009,19(11):1635-1641
[19] Elhamifar E,Vidal R.Sparse subspace clustering[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2009(CVPR 2009).IEEE,2009:2790-2797
[20] Zhang L,Yang M,Feng X,et al.Collaborative representation based classification for face recognition [J].arXiv preprint arXiv:1204.2358,2012
[21] 朱杰,杨万扣,唐振民.基于字典学习的核稀疏表示人脸识别方法[J].模式识别与人工智能,2012,25(5):859-864
[22] Xu Y,Zhu X J,Li Z M.Using the original and symmetrical face training samples to perform representation based two-step face recognition [J].Pattern Recognition,2013,46:1151-1158
[23] 胡正平,宋淑芬.基于全局和分离部件融合的双L1稀疏表示人脸图像识别算法[J].模式识别与人工智能,2012,25(2):78-83
[24] Fang X Z,Xu Y,Li X L,et al.Locality and similarity preserving embedding for feature selection [J].Neurocomputing,2014,128:304-315
[25] Tibshirani R.Regression shrinkage and selection via the lasso [J].Journal of the Royal Statistical Society.Series B (Methodological),1996:267-288
[26] Efron B,Hastie T,Johnstone I,et al.Least angle regression[J].The Annals of statistics,2004,32(2):407-499
[27] Moghadam A E,Shirani S.Matching pursuit-based region-of-interest image coding [J].IEEE Transactions on Image Processing,2007,16(2):406-415
[28] Needell D,Tropp J A.CoSaMP:Iterative signal recovery from incomplete and inaccurate samples [J].Applied and Computational Harmonic Analysis,2009,26(3):301-321
[29] ORL database.http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
[30] FERET database.http://www.itl.nist.gov/iad/huma-nid/feret/feret?master.html
[31] AR database.http://cobweb.ecn.purdue.edu/~aleix/al-eix?face?DB.html

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed