Wavelet-Based Colour Texture Retrieval Using the Kullback-Leibler Divergence Between Bivariate Generalized Gaussian Models (original) (raw)
Related papers
2008 15th IEEE International Conference on Image Processing, 2008
This contribution concerns the retrieval of colour texture. The interband correlation structure is considered by modeling the heavy-tailed image wavelet histograms with a multivariate generalized Gaussian. As a similarity measure we propose to use the Rao geodesic distance, which, in contrast to the Kullback-Leibler divergence, exists in a closed form for any fixed value of the shape parameter of the distribution. We apply this in several retrieval experiments. The modeling of the interband correlation significantly increases retrieval rates, while the geodesic distance is shown to outperform the Kullback-Leibler divergence. A multivariate Laplace distribution yields better results than a Gaussian, indicating the potential of a model with variable shape parameter together with the geodesic distance.
2012 19th IEEE International Conference on Image Processing, 2012
This paper presents a new multivariate elliptical distribution, namely the multivariate generalized Gamma times an Uniform (MGΓU) distribution. Because it generalizes the multivariate generalized Gaussian distribution (MGGD), the MGΓU distribution is able to fit a wider range of signals. For the bivariate case, we provide a closed-form of the Kullback-Leibler divergence (KLD). We propose the MGΓU distribution for modeling chrominance wavelet coefficients and exercise it in a texture retrieval experiment. A comparative study between some multivariate models on the VisTex and Outex image database is conducted and reveals that the use of the MGΓU distribution of chromiance wavelet coefficient allows an indexing gain compared to other classical approaches such as MGGD and Copula based model).
2008
In this work, we present a texture-image retrieval approach, which is based on the idea of measuring the Kullback-Leibler divergence between the marginal distributions of complex wavelet coefficient magnitudes. We employ Kingsbury's Dual-Tree Complex Wavelet Transform for image decomposition and propose to model the detail subband coefficient magnitudes by either two-parameter Weibull or Gamma distributions for which we provide closed-form solutions to the Kullback-Leibler divergence. The experimental results indicate that our approach can achieve higher retrieval rates than the classical approach of using the pyramidal Discrete Wavelet Transform together with the Generalized Gaussian model for detail subband coefficients.
A joint model of complex wavelet coefficients for texture retrieval
2009
We present a Copula-based statistical model of complex wavelet coefficient magnitudes for color texture image retrieval. Our model is based on two-parameter Weibull distributions and a multivariate Student t Copula. For similarity measurement we employ a Monte- Carlo approach to approximate the Kullback-Leibler divergence between two models. The experimental retrieval results show that the incorporation of the dependency structure between subbands significantly improves retrieval accuracy compared to previous approaches.
Gaussian Copula Multivariate Modeling for Texture Image Retrieval Using Wavelet Transforms
IEEE Transactions on Image Processing, 2014
In the framework of texture image retrieval, a new family of stochastic multivariate modeling is proposed based on Gaussian Copula and wavelet decompositions. We take advantage of the copula paradigm which makes it possible to separate dependency structure from marginal behavior. We introduce two new multivariate models using respectively generalized Gaussian and Weibull densities. These models capture both the subband marginal distributions and the correlation between wavelet coefficients. We derive, as a similarity measure, a closed form expression of the Jeffrey divergence between Gaussian Copula-based multivariate models. Experimental results on well-known databases show significant improvements in retrieval rates using the proposed method compared to the best known state-of-the-art approaches.
2010
This paper presents a texture descriptor based on the fine detail coefficients at three resolution levels of a traslation invariant undecimated wavelet transform. First, we consider vertical and horizontal wavelet detail coefficients at the same position as the components of a bivariate random vector, and the magnitude and angle of these vectors are computed. The magnitudes are modeled by a Generalized Gamma distribution. Their parameters, together with the circular histograms of angles, are used to characterize each texture image of the database. The Kullback-Leibler divergence is used as the similarity measurement. Retrieval experiments, in which we compare two wavelet transforms, are carried out on the Brodatz texture collection. Results reveal the good performance of this wavelet-based texture descriptor obtained via the Generalized Gamma distribution.
Multivariate statistical modeling for texture analysis using wavelet transforms
2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010
This paper deals with texture modeling for classification or retrieval systems using multivariate statistical features. We propose to model neighborhoods of wavelet coefficients using Spherically Invariant Random Vectors (SIRVs). Under this multivariate model we provide a closed form of Kullback-Leibler divergence between joint distributions to measure similarity. The performances of the proposed model in retrieval are conducted on the VisTex image database aiming to compare the recognition rates with conventional approach of using univariate models such as the Generalized Gaussian distribution and with a recent multivariate model of wavelet coefficients called Multivariate Bessel K forms (MBKF).
IEEE Access, 2019
This paper presents a new statistical model for texture retrieval in the complex wavelet domain. For this purpose, a finite mixture of Weibull distributions (MoWbl) is proposed to characterize the statistical distribution of magnitudes of complex wavelet coefficients. Despite the ability of the mixture model on capturing a wide range of distribution shapes, choosing an appropriate number of mixture components is a challenging task. To this end, we adopt an unsupervised learning of the model parameters based on the Figueiredo-Jain algorithm and maximum-likelihood estimates. As found in all retrieval statistical-based frameworks, the presence of a similarity measure is trivial. Generally, the failure of a retrieval mixture based system is closely related to the choice of the similarity measure that relies mainly on approximations of some divergences and distances. To overcome this limitation, we propose a canonical form of Weibull distribution which allows us to develop an analytic expression of Cauchy-Schwarz divergence (CSD) for MoWbl distributions. Experiments, conducted on three popular datasets, show that the proposed model yields better performance in terms of goodness-of-fit, retrieval, and execution time compared to some related statistical models for texture retrieval.
Multivariate Generalized Gamma Distribution for Content Based Image Retrieval
Journal of Convergence Information Technology, 2012
This paper deals with the joint modeling of color textures in the context of Content Based Image Retrieval (CBIR). We propose a generic multivariate model based on the Generalized Gamma distribution to describe the marginal behavior of texture wavelet detail subbands. Then the information of dependence across color components is incorporated in the modeling process using the Gaussian copula. The multivariate Generalized Gamma distribution (D MG) is advantageous in term of flexibility when compared with other joint models. As similarity measure, we propose a closed-form of the Kullback-leibler (KL) divergence between two Ds MG. Performances of the CBIR system show the superiority of the proposed model over a variety of multivariate models.
Gaussian mixture models of texture and colour for image database retrieval
2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).
We introduce Gaussian mixture models of 'structure' and colour features in order to classify coloured textures in images, with a view to the retrieval of textured colour images from databases. Classifications are performed separately using structure and colour and then combined using a confidence criterion. We apply the models to the VisTex database and to the classification of man-made and natural areas in aerial images. We compare these models with others in the literature, and show an overall improvement in performance.