Abstract
A transfer learning approach for multidimensional parametric mixture random field-based textural representation is introduced. The proposed transfer learning approach allows alleviating the multidimensional mixture models requirement for sufficiently large, but not always available, learning data sets. These compound random field models consist of an underlying structure model that controls transitions between several sub-models, each of them has different characteristics. The structure model proposed is a two-dimensional probabilistic mixture model, either of the Bernoulli or Gaussian mixture type. Local textures are modeled using the fully multispectral three-dimensional Gaussian mixture sub-models. Both presented compound random field models allow the reproduction of, compresses, edits, and enlarges a given measured color, multispectral, or bidirectional texture function (BTF) texture so that ideally, both measured and synthetic textures are visually indiscernible.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the em algorithm. J. Roy. Stat. Soc. B 39(1), 1–38 (1977)
Figueiredo, M., Leitao, J.: Unsupervised image restoration and edge location using compound Gauss - Markov random fields and the mdl principle. IEEE Trans. Image Process. 6(8), 1089–1102 (1997)
Geman, S., Geman, D.: Stochastic relaxation, gibbs distributions and Bayesian restoration of images. IEEE Trans. Pattern Anal. Mach. Intell. 6(11), 721–741 (1984)
Grim, J., Haindl, M.: A discrete mixtures colour texture model. In: Chantler, M. (ed.) Texture 2002, The 2nd International Workshop on Texture Analysis and Synthesis, pp. 59–62. Heriot-Watt University, Glasgow (2002). http://citeseer.ist.psu.edu/533346.html
Grim, J., Haindl, M.: Texture modelling by discrete distribution mixtures. Comput. Stat. Data Anal. 41(3–4), 603–615 (2003)
Haindl, M., Grim, J., Somol, P., Pudil, P., Kudo, M.: A Gaussian mixture-based colour texture model. In: Kittler, J., Petrou, M., Nixon, M. (eds.) Proceedings of the 17th IAPR International Conference on Pattern Recognition, vol. III, pp. 177–180. IEEE Press, Los Alamitos (2004). http://dx.doi.org/10.1109/ICPR.2004.1334497
Haindl, M., Havlíček, V.: A multiscale colour texture model. In: Kasturi, R., Laurendeau, D., Suen, C. (eds.) Proceedings of the 16th International Conference on Pattern Recognition, pp. 255–258. IEEE Computer Society, Los Alamitos (2002). http://dx.doi.org/10.1109/ICPR.2002.1044676
Haindl, M., Havlíček, V.: A compound MRF texture model. In: Proceedings of the 20th International Conference on Pattern Recognition, ICPR 2010, pp. 1792–1795. IEEE Computer Society CPS, Los Alamitos (2010).https://doi.org/10.1109/ICPR.2010.442, http://doi.ieeecomputersociety.org/10.1109/ICPR.2010.442
Haindl, M., Remeš, V., Havlíček, V.: Potts compound markovian texture model. In: Proceedings of the 21st International Conference on Pattern Recognition, ICPR 2012, pp. 29–32. IEEE Computer Society CPS, Los Alamitos (2012)
Haindl, M.: Visual data recognition and modeling based on local Markovian models. In: Florack, L., Duits, R., Jongbloed, G., van Lieshout, M.-C., Davies, L. (eds.) Mathematical Methods for Signal and Image Analysis and Representation. CIV, vol. 41, pp. 241–259. Springer, London (2012). https://doi.org/10.1007/978-1-4471-2353-8_14
Haindl, M., Filip, J.: Visual Texture. Advances in Computer Vision and Pattern Recognition. Springer-Verlag, London (2013). https://doi.org/10.1007/978-1-4471-4902-6
Haindl, M., Havlíček, V.: A plausible texture enlargement and editing compound markovian model. In: Salerno, E., Cetin, A., Salvetti, O. (eds.) Computational Intelligence for Multimedia Understanding, Lecture Notes in Computer Science, vol. 7252, pp. 138–148. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-32436-9_12, http://www.springerlink.com/content/047124j43073m202/
Haindl, M., Havlíček, V.: Two compound random field texture models. In: Beltrán-Castañón, C., Nyström, I., Famili, F. (eds.) CIARP 2016. LNCS, vol. 10125, pp. 44–51. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52277-7_6
Haindl, M., Havlíček, V.: BTF compound texture model with fast iterative non-parametric control field synthesis. In: di Baja, G.S., Gallo, L., Yetongnon, K., Dipanda, A., Castrillon-Santana, M., Chbeir, R. (eds.) Proceedings of the 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS 2018), pp. 98–105. IEEE Computer Society CPS, Los Alamitos (2018). https://doi.org/10.1109/SITIS.2018.00025
Haindl, M., Havlíček, V.: BTF compound texture model with non-parametric control field. In: The 24th International Conference on Pattern Recognition (ICPR 2018), pp. 1151–1156. IEEE (2018). http://www.icpr2018.org/
Haindl, M., Havlíček, V., Grim, J.: Probabilistic discrete mixtures colour texture models. In: Ruiz-Shulcloper, J., Kropatsch, W.G. (eds.) CIARP 2008. LNCS, vol. 5197, pp. 675–682. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-85920-8_82
Haindl, M., Havlíček, V., Grim, J.: Probabilistic mixture-based image modelling. Kybernetika 46(3), 482–500 (2011). http://www.kybernetika.cz/content/2011/3/482/paper.pdf
Haindl, M., Remeš, V., Havlíček, V.: BTF potts compound texture model, vol. 9398, pp. 939807-1–939807-11. SPIE, Bellingham (2015). https://doi.org/10.1117/12.2077481
Jeng, F.C., Woods, J.W.: Compound Gauss-Markov random fields for image estimation. IEEE Trans. Signal Process. 39(3), 683–697 (1991)
Molina, R., Mateos, J., Katsaggelos, A., Vega, M.: Bayesian multichannel image restoration using compound Gauss-Markov random fields. IEEE Trans. Image Process. 12(12), 1642–1654 (2003)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2017). https://doi.org/10.1109/TKDE.2009.191
Singh, R., Vatsa, M., Patel, V.M., Ratha, N.: Domain Adaptation for Visual Understanding. Springer, Heidelberg (2020). https://doi.org/10.1007/978-3-030-30671-7
Torrey, L., Shavlik, J.: Transfer learning. In: Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, pp. 242–264. IGI Global (2010)
Weiss, K., Khoshgoftaar, T.M., Wang, D.D.: A survey of transfer learning. J. Big Data 3(1), 1–40 (2016). https://doi.org/10.1186/s40537-016-0043-6
Wu, J., Chung, A.C.S.: A segmentation model using compound Markov random fields based on a boundary model. IEEE Trans. Image Process. 16(1), 241–252 (2007)
Acknowledgements
The Czech Science Foundation project GAČR 19-12340S supported this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Haindl, M., Havlíček, V. (2020). Transfer Learning of Mixture Texture Models. In: Nguyen, N.T., Hoang, B.H., Huynh, C.P., Hwang, D., Trawiński, B., Vossen, G. (eds) Computational Collective Intelligence. ICCCI 2020. Lecture Notes in Computer Science(), vol 12496. Springer, Cham. https://doi.org/10.1007/978-3-030-63007-2_65
Download citation
DOI: https://doi.org/10.1007/978-3-030-63007-2_65
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63006-5
Online ISBN: 978-3-030-63007-2
eBook Packages: Computer ScienceComputer Science (R0)