Texture Classification with Fisher Kernel Extracted from the Continuous Models of RBM

Tayyaba Azim, Mahesan Niranjan

2014

Abstract

In this paper, we introduce a novel technique of deriving Fisher kernels from the Gaussian Bernoulli restricted Boltzmann machine (GBRBM) and factored 3-way restricted Boltzmann machine (FRBM) to yield better texture classification results. GBRBM and FRBM, both, are stochastic probabilistic models that have already shown their suitability for modelling real valued continuous data, however, they are not efficient models for classification based on their likelihood performances (Jaakkola and Haussler, 1999; Azim and Niranjan, 2013). We induce discrimination in these models with the help of Fisher kernel that is constructed from the gradients of the parameters of the generative model. From the empirical results shown on two different texture data sets, i.e. Emphysema and Brodatz, we demonstrate how a useful texture classifier could be built from a very compact generative model that represents the data in the Fisher score space discriminately. The proposed discriminative technique allows us to achieve competitive classification performance on texture data sets, without expanding the size of the generative model with large number of hidden units. Also, comparative analysis shows that factored 3-way RBM is a good representative model of textures, giving rise to a Fisher score space that is less sparse and efficient for classification.

Paper Citation

in Harvard Style

Azim T. and Niranjan M. (2014). Texture Classification with Fisher Kernel Extracted from the Continuous Models of RBM . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 684-690. DOI: 10.5220/0004857506840690

in Bibtex Style

@conference{visapp14,
author={Tayyaba Azim and Mahesan Niranjan},
title={Texture Classification with Fisher Kernel Extracted from the Continuous Models of RBM},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={684-690},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004857506840690},
isbn={978-989-758-004-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Texture Classification with Fisher Kernel Extracted from the Continuous Models of RBM
SN - 978-989-758-004-8
AU - Azim T.
AU - Niranjan M.
PY - 2014
SP - 684
EP - 690
DO - 10.5220/0004857506840690