Abstract
Texture is an important property of images, and a key component for human visual perception. In this work, based on several feature learning models and deep architectures, we study the visual texture perception problem, which is helpful for understanding both the impact of texture itself and the basic mechanisms of human visual systems. Through a series of psychophysical experiments, we find that 12 perceptual features are significant to describe the texture images with regard to the human perceptions. Hence, we represent each texture image with a 12-dimensional vector, corresponding to the values of the 12 perceptual features. To improve the learnablity of existing feature learning models, we propose a set of deep architectures to learn compact representations of the texture perceptual features. Extensive experiments on texture images classification demonstrate the effectiveness of both the feature learning models and the deep architectures. In particular, the advantage of deep architectures over existing feature learning models is shown.
Keywords
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
Chang, C.C., Lin, C.J.: Libsvm: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST) 2(3), 27 (2011)
Durgin, F.: Texture contrast aftereffects are monocular, texture density aftereffects are binocular. Vision Research 41, 2619–2630 (2001)
Gurnsey, R., Fleet, D.: Texture space. Vision Research 41, 745–757 (2001)
Heeger, D., Bergen, J.: Pyramid-based Texture Analysis/Synthesis. In: SIGGRAPH, pp. 229–238. ACM (1995)
Hinton, G., Roweis, S.: Stochastic Neighbor Embedding. In: NIPS, vol. 2, pp. 833–840 (2002)
Hinton, G., Salakhutdinov, R.: Reducing the Dimensionality of Data with Neural Networks. Science 313(5786), 504–507 (2006)
Jolliffe, I.: Principal Component Analysis, 2nd edn. Springer (October 2002)
Kingdom, F., Hayes, A., Field, D.: Sensitivity to contrast histogram differences in synthetic wavelet-textures. Vision Research 41, 585–598 (2001)
Kruskal, J., Wish, M.: Multidimensional Scaling, vol. 11. Sage (1978)
Landy, M., Graham, N.: Visual Perception of Texture. In: The Visual Neurosciences, pp. 1106–1118. MIT Press (2004)
Lawrence, N.: Gaussian Process Latent Variable Models for Visualisation of High Dimensional Data. In: NIPS, vol. 2, p. 5 (2003)
Liu, J., Dong, J., Qi, L., Chantler, M.: Identifying perceptual features of procedural textures. In: ECVP (2013)
van der Maaten, L.: An Introduction to Dimensionality Reduction Using MATLAB. Report 1201(07-07), 62 (2007)
Mekuz, N., Tsotsos, J.K.: Parameterless isomap with adaptive neighborhood selection. In: Franke, K., Müller, K.-R., Nickolay, B., Schäfer, R. (eds.) DAGM 2006. LNCS, vol. 4174, pp. 364–373. Springer, Heidelberg (2006)
Rao, A., Lohse, G.: Towards a Texture Naming System: Identifying Relevant Dimensions of Texture. Vision Research 36, 1649–1669 (1996)
Salakhutdinov, R., Hinton, G.: Deep Boltzmann Machines. In: AISTATS, pp. 448–455 (2009)
Sammon, J.: A Nonlinear Mapping for Data Structure Analysis. IEEE Transactions on Computers 18(5), 401–409 (1969)
Tipping, M., Bishop, C.: Probabilistic Principal Component Analysis. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 61(3), 611–622 (1999)
Wolfson, S., Landy, M.: Examining Edge- and Region-based Texture Mechanisms. Vision Research 38(3), 439–446 (1998)
Zhang, T., Yang, J., Zhao, D., Ge, X.: Linear Local Tangent Space Alignment and Application to Face Recognition. Neurocomputing 70(7), 1547–1553 (2007)
Zhang, Z., Zha, H.: Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment. SIAM J. Scientific Computing 26(1), 313–338 (2004)
Zhong, G., Cheriet, M.: Large Margin Low Rank Tensor Analysis. Neural Computation 26(4), 761–780 (2014)
Zhong, G., Li, W.J., Yeung, D.Y., Hou, X., Liu, C.L.: Gaussian Process Latent Random Field. In: AAAI (2010)
Zhong, G., Liu, C.L.: Error-Correcting Output Codes Based Ensemble Feature Extraction. Pattern Recognition 46(4), 1091–1100 (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zheng, Y., Zhong, G., Liu, J., Cai, X., Dong, J. (2014). Visual Texture Perception with Feature Learning Models and Deep Architectures. In: Li, S., Liu, C., Wang, Y. (eds) Pattern Recognition. CCPR 2014. Communications in Computer and Information Science, vol 483. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45646-0_41
Download citation
DOI: https://doi.org/10.1007/978-3-662-45646-0_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-45645-3
Online ISBN: 978-3-662-45646-0
eBook Packages: Computer ScienceComputer Science (R0)