Gaussian Copula Multivariate Modeling for Image Texture Retrieval Using Wavelet Transforms

Abstract : 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 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 density. These models capture both the subband marginal distributions and the correlation between wavelet coefficients. We derive, as a similarity measure, a closed form solution of the Jeffrey divergence between Gaussian Copula based multivariate models. Experimental results on the well-known databases show significant improvements in retrieval rates using the proposed method compared to the best known state-of-the-art approaches.
Complete list of metadatas

Cited literature [57 references]  Display  Hide  Download

https://hal.inria.fr/hal-00727127
Contributor : Nour-Eddine Lasmar <>
Submitted on : Tuesday, March 25, 2014 - 6:24:44 PM
Last modification on : Thursday, March 15, 2018 - 9:36:02 AM
Long-term archiving on : Wednesday, June 25, 2014 - 1:05:49 PM

File

TIP_201403_single_column.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Nour-Eddine Lasmar, Yannick Berthoumieu. Gaussian Copula Multivariate Modeling for Image Texture Retrieval Using Wavelet Transforms. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2014, 23 (5), pp.2246 - 2261. ⟨10.1109/TIP.2014.2313232⟩. ⟨hal-00727127v3⟩

Share

Metrics

Record views

509

Files downloads

662