Abstract
Dimensionality reduction plays a major role in face recognition. Discriminant analysis (DA) and principal component analysis (PCA) are two of the most important approaches in this field. In particular, subclass discriminant analysis (SDA) is a well-known scheme for feature extraction and dimensionality reduction. It is widely used in many high-dimensional data-driven applications, namely face recognition and image retrieval. It is also found to be applicable under various scenarios. However, it has high cost in time and space given the need for an eigendecomposition involving the scatter matrices, known as the singularity problem. This limitation is caused by the high-dimensional space of data, particularly when dimensions exceed the number of observations. Recent advances widely reported that 2D methods with matrix-based representation perform better than the traditional 1D vector-based ones. In this paper, we propose a novel 2D-SDA algorithm to avoid the “curse of dimensionality” and address the singularity issue. The performance of the proposed algorithm is evaluated for face recognition in terms of recognition performance and computational cost. Experiments are conducted on four benchmark face databases and compared to several competitive 1D and 2D methods based on PCA and DA. Results show that 2DSVD achieves the best recognition performance at low dimensions. In particular, 2D-SDA works significantly better on large-sized data sets where intra-class variation is the most important.
Similar content being viewed by others
References
Belhumeour PN, Hespanha JP, Kriegman DJ (1997) Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans Pattern Anal Mach Intell 19(7):711–720
Bouwmans T, Sobral A, Javed S, Jung SK, Zahzah EH (2017) Decomposition into low-rank plus additive matrices for background/foreground separation: a review for a comparative evaluation with a large-scale dataset. Comput Sci Rev 23:1–71
Chen CM, Song JT, Zhang SQ (2011) Face recognition method based on 2DPCA and compressive sensing. Comput Eng 33(22):176–178
Choi Y, Ozawa S, Lee M (2014) Incremental two-dimensional kernel principal component analysis. Neurocomputing 134:280–288
Da-Zheng ZYF (2011) An algorithm of feature extraction of face based on the weighted variation of 2DPCA. J Electron Inf Technol 33(4):769–774
Duda RO, Hart PE, Stork D (2000) Pattern classification. Wiley, Hoboken
Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Eugen 7:179–188
Fukunaga K (1990) Introduction to statistical pattern recognition, 2nd edn. Academic Press, London
He G, Tang Y, Fang B, Wang PS (2011) Bionic face recognition using Gabor transformation. Int J Pattern Recognit Artif Intell 25(3):391–402
Kong H, Wang L, Teoh EK, Li X, Wang JG (2005) Generalized 2D principal component analysis for face image representation and recognition. Neural Netw 18(5):585–594
Krzanowski WJ, Jonathan P, McCarthy WV, Thomas MR (1995) Discriminant analysis with singular covariance matrices: methods and applications to spectroscopic data. Appl Stat 27:101–115
Li M, Yuan B (2005) 2D-LDA: a statistical linear discriminant analysis for image matrix. Pattern Recognit Lett 26(5):527–532
Li X, Pang Y, Yuan Y (2010) L1-norm-based 2DPCA. IEEE Trans Syst Man Cybern Part B (Cybern) 40(4):1170–1175
Martínez A, Benavente R (1998) The AR face database. Computer Vision Center, Bellatera
Meng J, Zheng X (2013) Robust sparse 2D principal component analysis for object recognition. Appl Math Inf Sci 7(6):2509–2514
Nakouri H, Limam M (2015) Incremental generalized low rank approximation of matrices for visual learning and recognition. Pattern Recognit Image Anal 25(1):68–72
Nakouri H, El-Aroui MA, Limam M (2017) Robust low-rank approximation of images for background and foreground separation. In: Proceedings of the 18th international conference on parallel and distributed computing, applications and technologies, Taipei, Taiwan, pp 196–203
Phillips PJ, Wechsler H, Huang J, Rauss PJ (1998) The FERET database and evaluation procedure for face-recognition algorithms. Image Vis Comput 16(5):295–306
Peng H, Li B, Ling H, Hu W, Xiong W, Maybank SJ (2017) Salient object detection via structured matrix decomposition. IEEE Trans Pattern Anal Mach Intell 39(4):818–832
Rouabhia C, Tebbikh H (2011) Efficient face recognition based on weighted matrix distance metrics and 2DPCA algorithm. Arch Control Sci 21(2):207–221
Samaria F, Harter A (1994) Parameterisation of a stochastic model for human face identification. In: Proceedings of the IEEE workshop on applications of computer vision, pp 138–142
Turk M, Pentland A (1991) Eigenfaces for recognition. J Cogn Neurosci 3(1):71–86
Visani M, Garcia C, Jolion JM (2004) Two-dimensional-oriented linear discriminant analysis for face recognition. In: Proceedings of the international conference on computer vision and graphics, pp 1008–1017
Wahyuningrum RT, Damayanti F (2012) Efficient kernel-based two-dimensional principal component analysis for smile stages recognition. Telkomnika 10(1):113–118
Wang Q, Qin Z, Nie F, Yuan Y (2017) Convolutional 2D LDA for nonlinear dimensionality reduction. In: Proceedings of the 26th international joint conference on artificial intelligence, pp 2929–2935
Xiao X, Zhou Y (2019) Two-dimensional quaternion PCA and sparse PCA. IEEE Trans Neural Netw Learn Syst 30(7):2028–2042
Yang J, Zhang D, Frangi AF, Yan J (2004) Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Trans Pattern Anal Mach Intell 26(1):131–137
Ye J (2005) Generalized low rank approximations of matrices. Mach Learn 61(1):167–191
Zare A, Ozdemir A, Iwen MA, Aviyente S (2018) Extension of PCA to higher order data structures: an introduction to tensors. Tensor Decompos Tensor PCA 106(8):1341–1358
Zhang Y, Qi MX, Shang L (2012) Palmprint recognition based on two-dimensional gabor wavelet transform and two-dimensional principal component analysis. In: Advanced intelligent computing. Springer, Berlin, pp 405–411
Zhang H, Wu QMJ, Chow TWS, Zhao M (2012) A two-dimensional neighborhood preserving projection for appearance based face recognition. Pattern Recognit 45(5):1866–1876
Zhang QR (2014) Two-dimensional parameter principal component analysis for face recognition. Adv Mater Res 971–973:1838–1842
Zheng WS, Lai JH, Li SZ (2008) 1D-LDA vs. 2D-LDA: when is vector-based linear discriminant analysis better than matrix-based? Pattern Recognit 41(7):2156–2172
Zheng H, Pan L (2012) An improved block 2DPCA face recognition algorithm with L1-norm. Adv Mater Res 1639(457):1077–1082
Zhao M, Jia Z, Cai Y, Chen X, Gong D (2019) Advanced variations of two-dimensional principal component analysis for face recognition. Preprint submitted to Elsevier
Zhu M, Martinez AM (2006) Subclass discriminant analysis. IEEE Trans Pattern Anal Mach Intell 27(8):1274–1286
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Nakouri, H. Two-dimensional Subclass Discriminant Analysis for face recognition. Pattern Anal Applic 24, 109–117 (2021). https://doi.org/10.1007/s10044-020-00905-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-020-00905-5