Evaluation of Robust Feature Descriptors for Texture Classification

Authors: Jia-Hong Lee, Mei-Yi Wu, Hsien-Tsung Kuo

Abstract:

Texture is an important characteristic in real and synthetic scenes. Texture analysis plays a critical role in inspecting surfaces and provides important techniques in a variety of applications. Although several descriptors have been presented to extract texture features, the development of object recognition is still a difficult task due to the complex aspects of texture. Recently, many robust and scaling-invariant image features such as SIFT, SURF and ORB have been successfully used in image retrieval and object recognition. In this paper, we have tried to compare the performance for texture classification using these feature descriptors with k-means clustering. Different classifiers including K-NN, Naive Bayes, Back Propagation Neural Network , Decision Tree and Kstar were applied in three texture image sets － UIUCTex, KTH-TIPS and Brodatz, respectively. Experimental results reveal SIFTS as the best average accuracy rate holder in UIUCTex, KTH-TIPS and SURF is advantaged in Brodatz texture set. BP neuro network works best in the test set classification among all used classifiers.

Keywords: Texture classification, texture descriptor, SIFT, SURF, ORB.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1339083

References:

[1] R. Maani, S. Kalra, Y. H. Yang, Noise robust rotation invariant features for texture classification, Pattern Recognition, vol. 46, Iss. 8, Pp. 2103.
[2] R.M. Haralick, K. Shanmugam, I. Dinstein, Textural features for imageclassification, IEEE Transactions on Systems, Man and Cybernetics, vol. 3,1973.
[3] X. Tang,Texture information in run-length matrices, IEEE Transactions on Image Processing, vol. 7 , pp. 1602–1609, 1998.
[4] V. Murino, C. Ottonello, S. Pagnan, Noisy texture classification: a higher-order statistics approach, Pattern Recognition, vol. 31 , pp. 383– 393, 1998.
[5] R. Lopes, P. Dubois, I. Bhouri, M.H. Bedoui, S. Maouche, N. Betrouni, Local fractal and multifractal features for volumic texture characterization, Pattern Recognition, vol. 44, Iss. 8, pp. 1690-1697, 2011.
[6] T. Ojala, M. Pietikainen, T. Maenpaa,Multiresolution gray-scale and rotation invariant texture classification with local binary patterns, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24 , pp. 971–987, 2002.
[7] Y. Gui, M. Chen, L. Ma, Z. Chen, Texel based regular and near-regular texture characterization, in: International Conference on Multimedia and Signal Processing (CMSP), vol. 1, pp. 266–270, 2011.
[8] F.M. Khellah,Texture classification using dominant neighborhood structure. IEEE Transactions on Image Processing, vol. 20 , pp. 3270– 3279, 2011.
[9] F.S. Cohen, Z. Fan, M.A. Patel, Classification of rotated and scaled textured images using gaussian Markov random field models, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13 , pp. 192–202,1991.
[10] S. Yousefi, N. Kehtarnavaz, A new stochastic image model based on Markov random fields and its application to texture modeling, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1285–1288, 2011.
[11] R. Azencott, J.-P. Wang, L. Younes,Texture classification using windowed fourier filters, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, pp. 148–153,1997.
[12] B. Manjunath, W. Ma,Texture features for browsing and retrieval of image data, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, pp. 837–842, 1996.
[13] K. Jafari-Khouzani, H. Soltanian-Zadeh, Rotation-invariant multiresolution texture analysis using radon and wavelet transforms, IEEE Transactions on Image Processing, vol. 14, pp. 783–795, 2005.
[14] Herbert Bay, Andreas Ess, Tinne Tuytelaars, Luc Van Gool, Speeded-Up Robust Features (SURF), Computer Vision and Image Understanding, vol. 110, Iss. 3, pp. 346-359, 2008.
[15] D. G. Lowe,, “Object recognition from local scale-invariant features,” Proceedings of the International Conference on Computer Vision, vol. 2, pp. 1150–1157, 1999.
[16] W. Zhang, J.a Kosecka , Hierarchical building recognition, Journal Image and Vision Computing, Vol. 25, Iss. 5, pp. 704-716, 2007.
[17] J. MacQueen, L. M. LeCam and J. Neyman, Some methods of classification and analysis of multivariate observations, Proc. 5th Berkeley Symposium on Math., Stat., and Prob., p.p..281, 1967.
[18] UIUCTex dataset: http://www-cvr.ai.uiuc.edu/ponce_grp/data/texture_database/
[19] KTH-TIPS dataset: http://www.nada.kth.se/cvap/databases/kth-tips/documentation.html
[20] Brodatz dataset: http://www.ux.uis.no/~tranden/brodatz.html