Abstract
Inspired by the abilities of the human brain to identify elements from eyesight, the problem of dimensionality reduction in the domain of visual perception consists to extract a few number of features from an image database in order to recognize them. This paper presents an innovative feature extractor for images that considers their two dimensional topology to identify their relevant features. Numerical experiment applied to 70000 pictures representing handwritten digits, 698 images illustrating the face of a person under different poses and lighting directions, or 355 color holidays photos demonstrate the accuracy of our approach to drastically reduce the dimension while conserving the intelligible relations between data objects, reaching a classification of better quality from the reduced version of images than from their original full-size realizations.
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
Ahmed, N., Natarajan, T., Rao, K.R.: Discrete cosine transform. IEEE Transactions on Computers C-23(1), 90–93 (1974)
Medeiros, C.B., Joliveau, M., Jomier, G., De Vuyst, F.: Managing Sensor Data on Urban Traffic. In: Song, I.-Y., Piattini, M., Chen, Y.-P.P., Hartmann, S., Grandi, F., Trujillo, J., Opdahl, A.L., Ferri, F., Grifoni, P., Caschera, M.C., Rolland, C., Woo, C., Salinesi, C., Zimányi, E., Claramunt, C., Frasincar, F., Houben, G.-J., Thiran, P. (eds.) ER Workshops 2008. LNCS, vol. 5232, pp. 385–394. Springer, Heidelberg (2008)
Bauzer-Medeiros, C., Joliveau, M., Jomier, G., DeVuyst, F.: Managing sensor traffic data and forecasting unusual behaviour propagation. Geoinformatica (2009)
Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation 215(6), 1373–1396 (2003)
Canny, J.: A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence Archive 8(6), 679–698 (1986)
Choo, J., Reddy, C., Lee, H., Park, H.: p-isomap: An efficient parametric update for isomap for visual analytics. In: SIAM International Conference on Data Mining, pp. 502–513 (2010)
Christopoulos, C., Skodras, A., Ebrahimi, T.: The jpeg2000 still image coding system: An overview. IEEE Transactions on Consumer Electronics 46, 1103–1127 (2000)
CS-Incorporated: Graphics interchange format: Version 89a (1990)
Dumitras, A., Kossentini, F.: Fast and high performance image subsampling using feedforward neural networks. IEEE Transaction on Image Process 9(4), 720–728 (1997)
Fridrich, J.: A new steganographic method for palette-based images. In: Proc. of the IS & T PICS Conference, pp. 285–289 (1999)
Gashler, M., Ventura, D., Martinez, T.: Iterative non-linear dimensionality reduction with manifold sculpting. Advances in Neural Information Processing Systems 20, 513–520 (2008)
Izenman, A.J.: Modern multivariate statistical techniques. In: Regression, Classification & Manifold Learning. Springer Texts in Statistics, New York (2008)
Joliveau, M.: Reduction of urban traffic time series from georeferenced sensors, and extraction of spatio-temporal series. Ph.D. thesis, Ecole Centrale Des Arts Et Manufactures (Ecole Centrale Paris) (2008)
Joliveau, M., DeVuyst, F.: Space-time summarization of multisensor time series. case of missing data. In: Proc. of 2007 International Workshop on Spatial and Spatio-Temporal Data Mining, pp. 631–636 (2007)
Joliveau, M., DeVuyst, F.: Recherche de motifs spatio-temporels de cas atypiques pour le trafic routier urbain. In: Guilletet, F., Trousse, B. (eds.) Extraction et Gestion de Connaissances EGC 2008, Revue des Nouvelles Technologies de l’Information - RNTI - E11, vol. 2, pp. 523–534 (2008)
Jolliffe, I.: Principal component analysis. Springer, New York (1986)
Kruskal, J.B., Wish, M.: Multidimensional Scaling. Sage Publications (1978)
Lespinats, S., Fertil, B., Villemain, P., Herault, J.: Rankvisu: Mapping from the neighbourhood network. Neurocomputing 72(13-15), 2964–2978 (2009)
Lespinats, S., Verleysen, M., Giron, A., Fertil, B.: Dd-hds: a tool for visualization and exploration of high dimensional data. IEEE Transactions on Neural Networks 18(5), 1265–1279 (2007)
Lundmark, A., Wadstrmer, N., Li, H.: Hierarchical subsampling giving fractal regions. IEEE Transactions on Image Processing 10(1), 167–173 (2001)
Mardia, K., Kent, J., Bibby, J.: Multivariate analysis. Academic Press, London (1979)
Nadler, B., Lafon, S., Coifman, R., Kevrekidis, I.: Diffusion maps, spectral clustering and reaction coordinates of dynamical systems. Journal of Applied and Computational Harmonic Analysis 21, 113–127 (2006)
Randers-Pehrson, G.: Png (portable network graphics) specification, version 1.2 (1999)
Roweis, T., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)
Samal, A., Edwards, J.: Generalized hough transform for natural shapes. Pattern Recognition Letters 18(5), 473–480 (1997)
Samko, O., Marshall, A., Rosin, P.: Selection of the optimal parameter value for the isomap algorithm. Pattern Recogition Letter 27(9), 968–979 (2006)
Mallat, S.: A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(7), 674–693 (1989)
Tenenbaum, J., de Silva, V., Langford, J.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
Venna, J., Kaski, S.: Local multidimensional scaling. In: Neural Networks 2006 Special issue: Advances in self-organizing Maps–WSOM 2005, vol. 19, pp. 889–899 (2006)
Wallace, G.: The jpeg still picture compression standard. IEEE Transactions on Consumer Electronics 38(1), 18–34 (1992)
Young, S.: Alias-free image subsampling using fourier-based windowing methods. Optical Engineering 43, 843–855 (2004)
Zhang, Z., Zha, H.: Principal manifolds and nonlinear dimension reduction via tangent space alignment. SIAM Journal of Scientific Computing 26(1), 313–338 (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer Berlin Heidelberg
About this chapter
Cite this chapter
Joliveau, M. (2012). Identifying Relevant Features of Images from Their 2-D Topology. In: Guillet, F., Ritschard, G., Zighed, D. (eds) Advances in Knowledge Discovery and Management. Studies in Computational Intelligence, vol 398. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25838-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-25838-1_10
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25837-4
Online ISBN: 978-3-642-25838-1
eBook Packages: EngineeringEngineering (R0)