Abstract
Capturing dependencies in images in an unsupervised manner is important for many image-processing applications and understanding the structure of natural image signals. Linear generative models such as independent component analysis (ICA) have shown to capture low level features such as oriented edges in images. However ICA only captures linear dependency due to its linear model constraints and its modeling capability is limited. We propose a new method for capturing nonlinear dependencies in natural images. It is an extension of the linear ICA method and builds on a hierarchical representation. It makes use of lower level linear ICA representation and a subsequent mixture of Laplacian distribution for learning the nonlinear dependencies. The model is learned via the EM algorithm and it can capture variance correlation and high order structures in a consistent manner. We visualize the learned variance structure and demonstrate applications to image segmentation and denoising.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hinton, G.E., Sejnowski, T.J.: Unsupervised Learning: Foundations of Neural Computation (edited). MIT Press, Cambridge (1999)
Hyvarinen, A., Hoyer, P.O., Oja, E.: Image Denoising by Sparse Code Shrinkage. In: Haykin, S., Kosko, B. (eds.) Intelligent Signal Processing, IEEE Press, Los Alamitos (2001)
Bell, A.J., Sejnowski, T.J.: An information-maximization approach to blind separation and blind deconvolution. Neural Computation 7, 1129–1159 (1995)
Hyvarinen, A., Hoyer, P.O.: Emergence of phase and shift invariant features by decomposition of natural images into independent feature subspaces. Neural Computation 12(7) (2000)
Hyvarinen, A., Hoyer, P.O.: Topographic Independent Component Analysis. Neural Computation 13(7), 1525–1558 (2001)
Lewicki, M.S., Karklin, Y.: Learning higher-order structures in natural images. Network: Comput. Neural Syst. 14, 483–499 (2003)
Hyvaerinen, A., Oja, E.: A fast fixed-point algorithm for independent component analysis. Neural Computation 9, 1483–1492 (1997)
Simoncelli, E.P., Anderson, E.H.: Noise removal via Bayesian wavelet coring. In: Proceedings of the 3rd IEEE International Conf. on Image Processing, vol. 1, pp. 379–382 (1996)
Simoncelli, E.P.: Bayesian Denoising of Visual Images in the Wavelet Domain. In: Inference in Wavelet Based Models, Springer-Verlag, pp. 291–308 (1999) (in Bayesian)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: From error visibility to structural similarity. IEEE Trans. on Image Proc. 13(4) (April 2004)
Park, H.J., Lee, T.W.: Unsupervised learning of nonlinear dependencies in natural images. In: Intl. Journal of Image Science and Technology (2004) (to be published)
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
Park, HJ., Lee, TW. (2004). A Hierarchical ICA Method for Unsupervised Learning of Nonlinear Dependencies in Natural Images. In: Puntonet, C.G., Prieto, A. (eds) Independent Component Analysis and Blind Signal Separation. ICA 2004. Lecture Notes in Computer Science, vol 3195. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30110-3_158
Download citation
DOI: https://doi.org/10.1007/978-3-540-30110-3_158
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23056-4
Online ISBN: 978-3-540-30110-3
eBook Packages: Springer Book Archive