Journal Home > Volume 2 , Issue 4
Computational Visual Media 2016, 2(4): 367-377 https://doi.org/10.1007/s41095-016-0060-6
Research Article | Open Access | Issue | Published: 15 November 2016

Texture image classification with discriminative neural networks

Show Author's Information Yang Song1( ),  Qing Li1,  Dagan Feng1,  Ju Jia Zou2,  Weidong Cai1
School of Information Technologies, the University of Sydney, NSW 2006, Australia.
School of Computing, Engineering and Mathematics, Western Sydney University, Penrith, NSW 2751, Australia.
Keywords:
neural networks, texture classification, feature learning, feature transformation
Cite this article:
Song Y, Li Q, Feng D, et al. Texture image classification with discriminative neural networks. Computational Visual Media, 2016, 2(4): 367-377. https://doi.org/10.1007/s41095-016-0060-6
Download citation
EndNote(RIS)
BibTeX

633

Views

47

Downloads

Citations

21

Crossref

N/A

WoS

23

Scopus

0

CSCD

Abstract Full text About this article

Texture provides an important cue for many computer vision applications, and texture image classification has been an active research area over the past years. Recently, deep learning techniques using convolutional neural networks (CNN) have emerged as the state-of-the-art: CNN-based features provide a significant performance improvement over previous handcrafted features. In this study, we demonstrate that we can further improve the discriminative power of CNN-based features and achieve more accurate classification of texture images. In particular, we have designed a discriminative neural network-based feature transformation (NFT) method, with which the CNN-based features are transformed to lower dimensionality descriptors based on an ensemble of neural networks optimized for the classification objective. For evaluation, we used three standard benchmark datasets (KTH-TIPS2, FMD, and DTD) for texture image classification. Our experimental results show enhanced classification performance over the state-of-the-art.


menu
Abstract
Full text
Outline
About this article

Texture image classification with discriminative neural networks

Show Author's information Yang Song1( ), Qing Li1, Dagan Feng1, Ju Jia Zou2, Weidong Cai1
School of Information Technologies, the University of Sydney, NSW 2006, Australia.
School of Computing, Engineering and Mathematics, Western Sydney University, Penrith, NSW 2751, Australia.

Abstract

Texture provides an important cue for many computer vision applications, and texture image classification has been an active research area over the past years. Recently, deep learning techniques using convolutional neural networks (CNN) have emerged as the state-of-the-art: CNN-based features provide a significant performance improvement over previous handcrafted features. In this study, we demonstrate that we can further improve the discriminative power of CNN-based features and achieve more accurate classification of texture images. In particular, we have designed a discriminative neural network-based feature transformation (NFT) method, with which the CNN-based features are transformed to lower dimensionality descriptors based on an ensemble of neural networks optimized for the classification objective. For evaluation, we used three standard benchmark datasets (KTH-TIPS2, FMD, and DTD) for texture image classification. Our experimental results show enhanced classification performance over the state-of-the-art.

Keywords: neural networks, texture classification, feature learning, feature transformation

References(32)

[1]
Leung, T.; Malik, J. Representing and recognizing the visual appearance of materials using three-dimensional textons. International Journal of Computer Vision Vol. 43, No. 1, 29-44, 2001.
Google Scholar
[2]
Varma, M.; Garg, R. Locally invariant fractal features for statistical texture classification. In: Proceedings of IEEE 11th International Conference on Computer Vision, 1-8, 2007.
DOI
[3]
Malik, J.; Belongie, S.; Leung, T.; Shi, J. Contour and texture analysis for image segmentation. International Journal of Computer Vision Vol. 43, No. 1, 7-27, 2001.
DOI Google Scholar
[4]
Lazebnik, S.; Schmid, C.; Ponce, J. A sparse texture representation using local affine regions. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 27, No. 8, 1265-1278, 2005.
DOI Google Scholar
[5]
Zhang, J.; Marszalek, M.; Lazebnik, S.; Schmid, C. Local features and kernels for classification of texture and object categories: A comprehensive study. International Journal of Computer Vision Vol. 73, No. 2, 213-238, 2007.
DOI Google Scholar
[6]
Liu, L.; Fieguth, P.; Kuang, G.; Zha, H. Sorted random projections for robust texture classification. In: Proceedings of International Conference on Computer Vision, 391-398, 2011.
DOI
[7]
Timofte, R.; Van Gool, L. A training-free classification framework for textures, writers, and materials. In: Proceedings of the 23rd British Machine Vision Conference, Vol. 13, 14, 2012.
DOI
[8]
Sharma, G.; ul Hussain, S.; Jurie, F. Local higher-order statistics (LHS) for texture categorization and facial analysis. In: Computer Vision—ECCV 2012. Fitzgibbon, A.; Lazebnik, S.; Perona, P.; Sato, Y.; Schmid, C. Eds. Springer Berlin Heidelberg, 1-12, 2012.
DOI
[9]
Cimpoi, M.; Maji, S.; Kokkinos, I.; Mohamed, S.; Vedaldi, A. Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3606-3613, 2014.
DOI
[10]
Lowe, D. G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision Vol. 60, No. 2, 91-110, 2004.
DOI Google Scholar
[11]
Ojala, T.; Pietikainen, M.; Maenpaa, T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 24, No. 7, 971-987, 2002.
DOI Google Scholar
[12]
Sharan, L.; Liu, C.; Rosenholtz, R.; Adelson, E. H. Recognizing materials using perceptually inspired features. International Journal of Computer Vision Vol. 103, No. 3, 348-371, 2013.
DOI Google Scholar
[13]
Quan, Y.; Xu, Y.; Sun, Y.; Luo, Y. Lacunarity analysis on image patterns for texture classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 160-167, 2014.
DOI
[14]
Crosier, M.; Griffin, L. D. Using basic image features for texture classification. International Journal of Computer Vision Vol. 88, No. 3, 447-460, 2010.
DOI Google Scholar
[15]
Xu, Y.; Ji, H.; Fermüller, C. Viewpoint invariant texture description using fractal analysis. International Journal of Computer Vision Vol. 83, No. 1, 85-100, 2009.
DOI Google Scholar
[16]
Krizhevsky, A.; Sutskever, I.; Hinton, G. E. Imagenet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, 1097-1105, 2012.
[17]
Song, Y.; Cai, W.; Li, Q.; Zhang, F.; Feng, D.; Huang, H. Fusing subcategory probabilities for texture classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4409-4417, 2015.
[18]
Cimpoi, M.; Maji, S.; Vedaldi, A. Deep filter banks for texture recognition and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3828-3836, 2015.
DOI
[19]
Lin, T. Y.; Maji, S. Visualizing and understanding deep texture representations. arXiv preprint arXiv:1511.05197, 2015.
DOI Google Scholar
[20]
Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
Google Scholar
[21]
Van der MLJP, P. E. O.; van den HH, J. Dimensionality reduction: A comparative review. Tilburg, Netherlands: Tilburg Centre for Creative Computing, Tilburg University, Technical Report: 2009-005, 2009.
[22]
Cunningham, J. P.; Ghahramani, Z. Linear dimensionality reduction: Survey, insights, and generalizations. Journal of Machine Learning Research Vol. 16, 2859-2900, 2015.
Google Scholar
[23]
Hinton, G. E.; Salakhutdinov, R. R. Reducing the dimensionality of data with neural networks. Science Vol. 313, No. 5786, 504-507, 2006.
DOI Google Scholar
[24]
Wang, W.; Huang, Y.; Wang, Y.; Wang, L. Generalized autoencoder: A neural network framework for dimensionality reduction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 490-497, 2014.
DOI
[25]
Wang, Y.; Yao, H.; Zhao, S. Auto-encoder based dimensionality reduction. Neurocomputing Vol. 184, 232-242, 2016.
DOI Google Scholar
[26]
Caputo, B.; Hayman, E.; Mallikarjuna, P. Class-specific material categorization. In: Proceedings of the 10th IEEE International Conference on Computer Vision, Vol. 1, 1597-1604, 2005.
DOI
[27]
Sharan, L.; Rosenholtz, R.; Adelson, E. Material perception: What can you see in a brief glance? Journal of Vision Vol. 9, No. 8, 784, 2009.
DOI Google Scholar
[28]
Perronnin, F.; Sánchez, J.; Mensink, T. Improving the fisher kernel for large-scale image classification. In: Computer Vision—ECCV 2010. Daniilidis, K.; Maragos, P.; Paragios, N. Eds. Springer Berlin Heidelberg, 143-156, 2010.
DOI
[29]
Svozil, D.; Kvasnicka, V.; Pospichal, J. Introduction to multi-layer feed-forward neural networks. Chemometrics and Intelligent Laboratory Systems Vol. 39, No. 1, 43-62, 1997.
DOI Google Scholar
[30]
Vedaldi, A.; Lenc, K. Matconvnet: Convolutional neural networks for MATLAB. In: Proceedings of the 23rd ACM International Conference on Multimedia, 689-692, 2015.
DOI
[31]
Vedaldi, A.; Fulkerson, B. VLFeat: An open and portable library of computer vision algorithms. In: Proceedings of the 18th ACM International Conference on Multimedia, 1469-1472, 2010.
DOI
[32]
Chang, C.-C.; Lin, C.-J. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology Vol. 2, No. 3, Article No. 27, 2011.
DOI Google Scholar
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Revised: 02 August 2016
Accepted: 21 September 2016
Published: 15 November 2016
Issue date: December 2016

Copyright

© The Author(s) 2016

Acknowledgements

This work was supported in part by Australian Research Council (ARC) grants.

Rights and permissions

This article is published with open access at Springerlink.com

The articles published in this journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Other papers from this open access journal are available free of charge from http://www.springer.com/journal/41095. To submit a manuscript, please go to https://www.editorialmanager.com/cvmj.

Return