JOURNAL BROWSE
Search
Advanced SearchSearch Tips
Robust Multi-Layer Hierarchical Model for Digit Character Recognition
facebook(new window)  Pirnt(new window) E-mail(new window) Excel Download
 Title & Authors
Robust Multi-Layer Hierarchical Model for Digit Character Recognition
Yang, Jie; Sun, Yadong; Zhang, Liangjun; Zhang, Qingnian;
  PDF(new window)
 Abstract
Although digit character recognition has got a significant improvement in recent years, it is still challenging to achieve satisfied result if the data contains an amount of distracting factors. This paper proposes a novel digit character recognition approach using a multi-layer hierarchical model, Hybrid Restricted Boltzmann Machines (HRBMs), which allows the learning architecture to be robust to background distracting factors. The insight behind the proposed model is that useful high-level features appear more frequently than distracting factors during learning, thus the high-level features can be decompose into hybrid hierarchical structures by using only small label information. In order to extract robust and compact features, a stochastic 0-1 layer is employed, which enables the model`s hidden nodes to independently capture the useful character features during training. Experiments on the variations of Mixed National Institute of Standards and Technology (MNIST) dataset show that improvements of the multi-layer hierarchical model can be achieved by the proposed method. Finally, the paper shows the proposed technique which is used in a real-world application, where it is able to identify digit characters under various complex background images.
 Keywords
Digit character recognition;Multi-layer hierarchical;Neutral networks;Restricted Boltzmann Machine;Computer vision;
 Language
English
 Cited by
 References
1.
R. G. J. Wijnhoven and P. H. N. de With, “Identity Verification Using Computer Vision for Automatic Garage Door Opening,” IEEE Transactions Consumer Electron., vol. 57, no. 2, pp. 906-914, May. 2011. crossref(new window)

2.
N. Y. Lee and P. H. Ho, “Digital Signature with a Threshold Subliminal Channel,” IEEE Transactions Consumer Electron., vol. 49, no. 4, pp 1240-1242, Nov. 2003. crossref(new window)

3.
K. S. Yildirim, A. Ugur, and A. C. Kinaci, “Design and Implementation of a Software Presenting Information in DVB Subtitles in Various Forms,” IEEE Transactions Consumer Electron., vol. 53, no. 4 pp. 1656-1660, Nov. 2007. crossref(new window)

4.
S. D. Choi and S. Y. Lee, “3D Stroke Reconstruction and Cursive Script Recognition with Magnetometeraided Inertial Measurement Unit”, IEEE Transactions Consumer Electron., vol. 58, no. 2, pp. 661-669, May. 2012. crossref(new window)

5.
Muhammad Suhail Akhtar, Hammad A. Qureshi, “Handwritten Digit Recognition through Wavelet Decomposition and Wavelet Packet Decomposition,” in Proc. IEEE International Conference on Digital Information Management, Islamabad, Pakistan, pp. 143-148, Sep. 2013.

6.
Thomas Deselaers, Tobias Gass, Georg Heigold, and Hermann Ney, “Latent Log-linear Models for Handwritten Digit Classification,” IEEE Transactions Pattern Analysis and Machine Intelligence, vol. 34, no. 6, pp. 1105-1117, Jun. 2012. crossref(new window)

7.
R. Mittelman, H. Lee, B. Kuipers, and S. Savarese, “Weakly Supervised Learning of Mid-level Features with Beta-Bernoulli Process Restricted Boltzmann Machines”, in Proc. IEEE International Conference Computer Vision and Pattern Recognition, Portland, OR, USA, pp. 476-483, Jun. 2013.

8.
H. Cecotti and S. Vajda, “A Radial Neural Convolutional Layer for Multi-oriented Character Recognition,” in Proc. IEEE International Conference on Document Analysis and Recognition, Washington DC, USA, pp. 668-672, Aug. 2013.

9.
H. T. Phan, A. T. Duong, N. D. H. Le, S. T. Tran, “Hierarchical Sparse Autoencoder Using Linear Regression-based Features in Clustering for Handwritten Digit Recognition,” in Proc. International Symposium on Image and Signal Processing and Analysis, Trieste, Italy, pp. 183-188, Sep. 2013.

10.
H. Lee, R. Grosse, R. Ranganath, and A. Y. Ng, “Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations,” In Proc. International Conference on Machine Learning, Montreal, Canada, pp. 609-616, Jun. 2009.

11.
D. C. Ciresan, U. Meier, L. M. Gambardella, and J. Schmidhuber, “Convolutional Neural Network Committees for Handwritten Character Classification,” In Proc. IEEE International Conference on Document Analysis and Recognition, Beijing, China, pp. 1135-1139, Sep. 2011.

12.
D. C. Ciresan, U. Meier, and J. Schmidhuber, “Multicolumn Deep Neural Networks for Image Classification,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, pp. 3642-3649, Jun. 2012.

13.
A. Fischer and C. Igel, “An introduction to restricted Boltzmann machines,” Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, Springer Berlin Heidelberg, pp. 14-36. 2012.

14.
A. R. Mohamed, G. E. Dahl, and G. Hinton, “Acoustic Modeling Using Deep Belief Networks,” IEEE Trans. Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 14-22, Jan. 2012. crossref(new window)

15.
G. W. Taylor and G. E. Hinton, “Factored Conditional Restricted Boltzmann Machines for Modeling Motion Style,” In Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, Canada, pp. 1025-1032, Jun. 2009.

16.
M. Ranzato, J. Susskind, V. Mnih, and G. Hinton, “On Deep Generative Models with Applications to Recognition,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, USA, pp. 2857-2864, Jun. 2011.

17.
Variations on the MNIST handwritten digit dataset: http://www.iro.umontreal.ca/~lisa/twiki/bin/view.cgi/Public/MnistVariations. Oct. 23th 2012.

18.
Nair Vinod, Geoffrey Hinton, “Implicit mixtures of restricted Boltzmann machines,” Advances in neural information processing systems. pp. 1145-1152, 2009.

19.
P. Vincent, H. Larochelle, Y. Bengio, and P. A. Manzagol, “Extracting and Composing Robust Features with Denoising Autoencoders,” In Proc. International Conference on Machine learning, Helsinki, Finland, pp. 1096-1103, Jul. 2008.

20.
G. E. Hinton, “Training Products of Experts by Minimizing Contrastive Divergence,” Neural Computation, vol. 14, no. 8, pp. 1771-1800, Aug. 2002. crossref(new window)

21.
S. Rifai, P. Vincent, X. Muller, X. Glorot, and Y. Bengio, “Contractive Auto-encoders: Explicit Invariance During Feature Extraction,” In Proc. International Conference on Machine Learning, Bellevue, Washington, USA, pp. 833-840, Jun. 2011.

22.
B. Cheung and C. Sable, “Hybrid Evolution of Convolutional Networks,” In Proc. IEEE International Conference Machine Learning and Applications and Workshops, Hawaii, USA, vol. 1, pp. 293-297, Dec. 2011.