Abstract
Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to variations commonly encountered in image datasets. Using the basic discriminating autoencoder as a unit, we build a stacked architecture aimed at extracting relevant representation from the training data. The efficiency of our feature extraction algorithm ensures a high classification accuracy with even simple classification schemes like KNN (K-nearest neighbor). We demonstrate the superiority of our model for representation learning by conducting experiments on standard datasets for character/image recognition and subsequent comparison with existing supervised deep architectures like class sparse stacked autoencoder and discriminative deep belief network.
References
Qian Y, Ye M, Zhou J (2013) Hyperspectral image classification based on structured sparse logistic regression and three-dimensional wavelet texture features. IEEE Trans Geosci Remote Sens 51(4):2276–2291
Vigdor B, Lerner B (2006) Accurate and fast off and online fuzzy ARTMAP-based image classification with application to genetic abnormality diagnosis. IEEE Trans Neural Netw 17(5):1288–1300
Tao H, Hou C, Nie F, Jiao Y, Yi D (2016) Effective discriminative feature selection with nontrivial solution. IEEE Trans Neural Netw Learn Syst 27(4):796–808
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), vol 1. IEEE, pp 886–893
Cheung W, Hamarneh G (2007) N-sift: N-dimensional scale invariant feature transform for matching medical images. In: 2007 4th IEEE international symposium on biomedical imaging: from nano to macro. IEEE, pp 720–723
Ahonen T, Matas J, He C, Pietikäinen M (2009) Rotation invariant image description with local binary pattern histogram fourier features. In: Scandinavian conference on image analysis. Springer, Berlin, pp 61–70
Gunturk BK, Batur AU, Altunbasak Y, Hayes MH, Mersereau RM (2003) Eigenface-domain super-resolution for face recognition. IEEE Trans Image Process 12(5):597–606
Jing X-Y, Wong H-S, Zhang D (2006) Face recognition based on 2D Fisherface approach. Pattern Recogn 39(4):707–710
Zhang B, Fu M, Yan H (1998) Handwritten digit recognition by a mixture of local principal component analysis. Proc Neural Process Lett 8(3):241–252
Maria Joao, Amaro Joao, Falcao Gabriel, Alexandre Luís A (2016) Stacked autoencoders using low-power accelerated architectures for object recognition in autonomous systems. Neural Process Lett 43(2):445–458
Mohamed A-R, Dahl GE, Hinton G (2012) Acoustic modeling using deep belief networks. IEEE Trans Audio Speech Lang Process 20(1):14–22
Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2(1):1–127
Hinton GE, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554
Yu D, Deng L (2011) Deep learning and its applications to signal and information processing [exploratory dsp]. IEEE Signal Process Mag 28(1):145–154
Zhou S, Chen Q, Wang X (2013) Convolutional deep networks for visual data classification. Neural Process Lett 38(1):17–27
Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14(8):1771–1800
Bengio Y, Lamblin P, Popovici D, Larochelle H (2007) Greedy layer-wise training of deep networks. Adv Neural Inf Process Syst 19:153
Abbas HM (2004) Analysis and pruning of nonlinear auto-association networks. IEEE Proc Vis Image Signal Process 151(1):44–50
Bourlard H, Kamp Y (1988) Auto-association by multilayer perceptrons and singular value decomposition. Biol Cybern 59(4–5):291–294
Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol P-A (2010) Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11:3371–3408
Olshausen BA (1996) Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583):607–609
Längkvist M, Loutfi A (2012) Learning representations with a dynamic objective sparse autoencoder. In: Neural information processing systems
Lemme A, Reinhart RF, Steil JJ (2012) Online learning and generalization of parts-based image representations by non-negative sparse autoencoders. Neural Netw 33:194–203
Chen M, Weinberger KQ, Sha F, Bengio Y (2014) Marginalized denoising auto-encoders for nonlinear representations. In: ICML, pp 1476–1484
Razakarivony S, Jurie F (2014) Discriminative autoencoders for small targets detection. In: IAPR international conference on pattern recognition, pp 3528–3533
Wang J, Gao X (2015) Max–min distance nonnegative matrix factorization. Neural Netw 61:75–84
Zhang Q, Li B (2010) Discriminative K-SVD for dictionary learning in face recognition. In: 2010 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2691–2698
Jiang Z, Lin Z, Davis LS (2013) Label consistent K-SVD: learning a discriminative dictionary for recognition. IEEE Trans Pattern Anal Mach Intell 35(11):2651–2664
Larochelle H, Bengio Y (2008) Classification using discriminative restricted Boltzmann machines. In: Proceedings of the 25th international conference on machine learning. ACM, pp 536–543
Goldstein T, Osher S (2009) The split Bregman method for L1-regularized problems. SIAM J Imaging Sci 2(2):323–343
http://www.iro.umontreal.ca/~lisa/twiki/bin/view.cgi/Public/DeepVsShallowComparisonICML2007
Lawson CL, Hanson RJ (1995) Solving least squares problems, vol 15. SIAM, Philadelphia
Ng A (2011) Sparse autoencoder. CS294A lecture notes 72:1–19
Majumdar A, Vatsa M, Singh R (2017) Face recognition via class sparsity based supervised encoding. IEEE Trans Pattern Anal Mach Intell 39(6):1273–1280
Liu Y, Zhoub S, Chen Q (2011) Discriminative deep belief networks for visual data classification. Pattern Recogn 44(10–11):2287–2296
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
Gogna, A., Majumdar, A. Discriminative Autoencoder for Feature Extraction: Application to Character Recognition. Neural Process Lett 49, 1723–1735 (2019). https://doi.org/10.1007/s11063-018-9894-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-018-9894-5