Abstract
Human visual system can recognize superimposed graphical components with ease while sophisticated computer vision systems still struggle to recognize them. This may be attributed to the fact that the image recognition task is framed as a classification task where a classification model is commonly constructed from appearance features. Hence, superimposed components are perceived as a single image unit. It seems logical to approach the recognition of superimposed digits by employing an approach that supports construction/deconstruction of superimposed components. Here, we resort to a dictionary-based non-negative matrix factorization (NMF). The dictionary-based NMF factors a given superimposed digit matrix, V, into the combination of entries in the dictionary matrix W. The H matrix from \(V \approx WH\) can be interpreted as corresponding superimposed digits. This work investigates three different dictionary representations: pixels’ intensity, Fourier coefficients and activations from RBM hidden layers. The results show that (i) NMF can be employed as a classifier and (ii) dictionary-based NMF is capable of classifying superimposed digits with only a small set of dictionary entries derived from single digits.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The database is available from http://yann.lecun.com/exdb/mnist/, it consists of 60,000 training examples (roughly 6,000 different handwritten examples for each digit) and 10,000 testing examples (roughly 1,000 different handwritten examples for each digit).
References
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013). IEEE
Bottou, L., Cortes, C., Denker, J.S., Drucker, H., Guyon, I., Jackel, L.D., LeCun, Y., Müller, U.A., Säckinger, E., Simard, P., Vapnik, V.: Comparison of classifier methods: a case study in handwritten digit recognition. In: Proceedings of the 12th IAPR International. Conference on Pattern Recognition, vol. 2, pp. 77–82. Conference B: Computer Vision & Image Processing (1994)
Ciresan, D.C., Meier, U., Masci, J., Gambardella, L.M., Schmidhuber, J.: Flexible, high performance convolutional neural networks for image classification. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI 2011), pp. 1237–1242 (2011)
Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
Phon-Amnuaisuk, S.: Applying non-negative matrix factorization to classify superimposed handwritten digits. Procedia Comput. Sci. 24(2013), 261–267 (2013)
Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791 (1999)
Sohn, K., Lee, H.: Learning invariant representations with local transformations. In: Proceedings of the 29th International Conference on Machine Learning, ICML 2012, Edinburgh (2012)
Song, H.A., Kim, B.K., Xuan, T.L., Lee, S.Y.: Hierarchical feature extraction by multi-layer non-negative matrix factorization network for classification task. Neurocomputing 165, 63–74 (2015)
Lee, S.Y., Mozer, M.C.: Robust recognition of noisy and superimposed patterns via selective attention. In: Proceedings of the International Conference on Neural Information Processing Systems (NIPS 1999), pp. 31–37 (1999)
Zhou, Z., Wagner, A., Mobahi, H., Wright, J., Ma., Y.: Face recognition with contiguous occlusion using markov random fields. In: Proceedings of the International Conference on Computer Vision (ICCV 2009), pp. 1050–1057. IEEE (2009)
Tang, Y., Salakhutdinov, R., Hinton, G.: Robust Boltzmann machines for recognition and denoising. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012), pp. 2264–2271. IEEE (2012)
Acknowledgments
We wish to thank anonymous reviewers for their comments, which help improve this paper. We would like to thank the GSR office for their financial support given to this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Phon-Amnuaisuk, S., Lee, SY. (2016). Investigating a Dictionary-Based Non-negative Matrix Factorization in Superimposed Digits Classification Tasks. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9949. Springer, Cham. https://doi.org/10.1007/978-3-319-46675-0_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-46675-0_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46674-3
Online ISBN: 978-3-319-46675-0
eBook Packages: Computer ScienceComputer Science (R0)