Abstract
One of the most important challenges faced by computer vision is the almost unlimited possibilities of variation associated with the objects. It has been hypothesized that the brain represents image manifolds as manifolds of stable neural-activity patterns. In this paper, we explore the possibility of manifold representation with a set of topographically organized neurons with each representing a local linear manifold and capturing some local linear feature invariance. In particular, we propose to consider the local subspace learning at each neuron of the network from a Gaussian likelihood point of view. Robustness of the algorithm with respect to the learning rate issue is obtained by considering statistical efficiency. Compared to its predecessors, the proposed network is more adaptive and robust in learning globally nonlinear data manifolds, which is verified by experiments on handwritten digit image modeling.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Adibi, P., Safabakhsh, R.: Linear manifold topographic map formation based on an energy function with on-line adaptation rules. Neurocomputing 72, 1817–1825 (2009)
Atkeson, C.G., Moore, A.W., Schaal, S.: Locally weighted learning. Artificial Intelligence Review 11, 11–73 (1997)
Cai, D., He, X., Hu, Y., Han, J., Huang, T.: Learning a spatially smooth subspace for face recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–7 (2007)
Kohonen, T.: The adaptive-subspace SOM (ASSOM) and its use for the implementation of invariant feature detection. In: Proceedings of International Conference on Artificial Neural Networks, pp. 3–10 (1995)
Kohonen, T.: Self-Organizing Maps, 3rd edn. Springer, Heidelberg (2001)
Kohonen, T., Kaski, S., Lappalainen, H.: Self-organized formation of various invariant-feature filters in the adaptive-subspace SOM. Neural Computation 9, 1321–1344 (1997)
Laaksonen, J., Oja, E.: Subspace dimension selection and averaged learning subspace method in handwritten digit classification. In: Vorbrüggen, J.C., von Seelen, W., Sendhoff, B. (eds.) ICANN 1996. LNCS, vol. 1112, pp. 227–232. Springer, Heidelberg (1996)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86, 2278–2324 (1998)
Liu, Z.Q.: Adaptive subspace self-organizing map and its application in face recognition. International Journal of Image and Graphics 2, 519–540 (2002)
López-Rubio, E., Muñoz-Pérez, J., Gómez-Ruiz, J.A.: A principal components analysis self-organizing map. Neural Networks 17, 261–270 (2004)
Oja, E.: Subspace Methods of Pattern Recognition. Research Studies Press, Letchworth (1983)
Robbins, H., Monro, S.: A stochastic approximation method. The Annals of Mathematical Statistics 22, 400–407 (1951)
Roweis, S., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)
Seung, H.S., Lee, D.D.: The manifold ways of perception. Science 290, 2268–2269 (2000)
Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
Weng, J., Zhang, Y., Hwang, W.S.: Candid covariance-free incremental principal component analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 1034–1040 (2003)
Zhang, B., Fu, M., Yan, H., Jabri, M.: Handwritten digit recognition by adaptive-subspace self-organizing map (ASSOM). IEEE Transactions on Neural Networks 10, 939–945 (1999)
Zheng, H., Shen, W., Dai, Q., Hu, S., Lu, Z.M.: Learning nonlinear manifolds based on mixtures of localized linear manifolds under a self-organizing framework. Neurocomputing 72, 3318–3330 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zheng, H. (2011). Invariant Feature Set Generation with the Linear Manifold Self-organizing Map. In: Kimmel, R., Klette, R., Sugimoto, A. (eds) Computer Vision – ACCV 2010. ACCV 2010. Lecture Notes in Computer Science, vol 6495. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19282-1_54
Download citation
DOI: https://doi.org/10.1007/978-3-642-19282-1_54
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19281-4
Online ISBN: 978-3-642-19282-1
eBook Packages: Computer ScienceComputer Science (R0)