Abstract
Dimensionality reduction is an essential aspect of visual processing. Traditionally, linear dimensionality reduction techniques such as principle components analysis have been used to find low dimensional linear subspaces in visual data. However, sub-manifolds in natural data are rarely linear, and consequently many recent techniques have been developed for discovering non-linear manifolds. Prominent among these are Local Linear Embedding and Isomap. Unfortunately, such techniques currently use a naive appearance model that judges image similarity based solely on Euclidean distance. In visual data, Euclidean distances rarely correspond to a meaningful perceptual difference between nearby images. In this paper, we attempt to improve the quality of manifold inference techniques for visual data by modeling local neighborhoods in terms of natural transformations between images—for example, by allowing image operations that extend simple differences and linear combinations. We introduce the idea of modeling local tangent spaces of the manifold in terms of these richer transformations. Given a local tangent space representation, we then embed data in a lower dimensional coordinate system while preserving reconstruction weights. This leads to improved manifold discovery in natural image sets.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Tenenbaum, J., de Silva, V., Langford, J.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
Saul, L., Roweis, S.: Think globally, fit locally: Unsupervised learning of nonlinear manifolds. JMLR (2003)
Cox, T., Cox, M.: Multidimensional Scaling, 2nd edn. Chapman Hall, Boca Raton (2001)
Jolliffe, I.: Principal Component Analysis. Springer, Heidelberg (1986)
Lebanon, G.: Learning Riemannian metrics. In: Proceedings UAI (2003)
Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. In: Proceedings NIPS (2001)
Teh, Y.-W., Roweis, S.: Automatic alignment of local representations. In: Proceedings NIPS (2002)
Hinton, G., Roweis, S.: Stochastic neighbor embedding. In: Proc. NIPS (2002)
Frey, B., Jojic, N.: Estimating mixture models of images and inferring spatial transformations using the em algorithm. In: Proceedings CVPR (1999)
Frey, B., Jojic, N.: Transformed component analysis: joint estimation of spatial transformations and image components. In: Proceedings ICCV, vol. 2, pp. 1190–1196 (1999)
Frey, B., Jojic, N.: Transformation-invariant clustering and dimensionality reduction using em. To appear in IEEE PAMI (2003)
Simard, P., Le Cum, Y., Denker, J.: Efficient pattern recognition using a new transformation distance. In: Proceedings NIPS 5 (1993)
Black, M., Jepson, A.: EigenTracking: Robust matching and tracking of articulated objects using a view-based representation. International Journal of Computer Vision 26(1) (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ghodsi, A., Huang, J., Schuurmans, D. (2004). Transformation-Invariant Embedding for Image Analysis. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3024. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24673-2_42
Download citation
DOI: https://doi.org/10.1007/978-3-540-24673-2_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21981-1
Online ISBN: 978-3-540-24673-2
eBook Packages: Springer Book Archive