A statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval

This paper presents a texture descriptor based on wavelet frame transforms. At each position in the image, and for each resolution level, we consider both vertical and horizontal wavelet detail coefficients as the components of a bivariate random vector. The magnitudes and angles of these vectors ar...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Acevedo, Daniel G., Ruedin, Ana María Clara
Publicado: 2014
Materias:
Image retrieval
Rotation invariant
Statistical models
Texture descriptor
Wavelet frames
Equivalence classes
Graphic methods
Statistical methods
Wavelet analysis
Generalized gamma distribution
Kullback Leibler divergence
Retrieval performance
Statistical modeling
Von Mises distribution
Wavelet frame
Acceso en línea:https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_00313203_v47_n9_p2925_DeVes
http://hdl.handle.net/20.500.12110/paper_00313203_v47_n9_p2925_DeVes
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id paper:paper_00313203_v47_n9_p2925_DeVes
record_format dspace
spelling paper:paper_00313203_v47_n9_p2925_DeVes2023-06-08T14:57:00Z A statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval Acevedo, Daniel G. Ruedin, Ana María Clara Image retrieval Rotation invariant Statistical models Texture descriptor Wavelet frames Equivalence classes Graphic methods Statistical methods Wavelet analysis Generalized gamma distribution Kullback Leibler divergence Retrieval performance Rotation invariant Statistical modeling Texture descriptor Von Mises distribution Wavelet frame Image retrieval This paper presents a texture descriptor based on wavelet frame transforms. At each position in the image, and for each resolution level, we consider both vertical and horizontal wavelet detail coefficients as the components of a bivariate random vector. The magnitudes and angles of these vectors are computed. At each level the empirical histogram of magnitudes is modeled by a Generalized Gamma distribution, and the empirical histogram of angles is modeled by a different version of the von Mises distribution that accounts for histograms with 2 modes. Each texture is characterized by few parameters. A new distance is presented (based on the Kullback-Leibler divergence) that allows giving relative importance to each model and to each resolution level. This distance is later conveniently adapted to provide for rotation invariance, by establishing equivalence classes over distributions of angles. Through a broad set of experiments on three different image databases, we demonstrate that our new descriptor and distance measure can be successfully applied in the context of texture retrieval. We compare our system to several relevant methods in this field in terms of retrieval performance and number of parameters used by each method. We also include some classification tests. In all the tests, we obtain superior retrieval rates for a set of fewer parameters involved. © 2014 Elsevier Ltd. Fil:Acevedo, D. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Ruedin, A. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. 2014 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_00313203_v47_n9_p2925_DeVes http://hdl.handle.net/20.500.12110/paper_00313203_v47_n9_p2925_DeVes
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic Image retrieval
Rotation invariant
Statistical models
Texture descriptor
Wavelet frames
Equivalence classes
Graphic methods
Statistical methods
Wavelet analysis
Generalized gamma distribution
Kullback Leibler divergence
Retrieval performance
Rotation invariant
Statistical modeling
Texture descriptor
Von Mises distribution
Wavelet frame
Image retrieval
spellingShingle Image retrieval
Rotation invariant
Statistical models
Texture descriptor
Wavelet frames
Equivalence classes
Graphic methods
Statistical methods
Wavelet analysis
Generalized gamma distribution
Kullback Leibler divergence
Retrieval performance
Rotation invariant
Statistical modeling
Texture descriptor
Von Mises distribution
Wavelet frame
Image retrieval
Acevedo, Daniel G.
Ruedin, Ana María Clara
A statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval
topic_facet Image retrieval
Rotation invariant
Statistical models
Texture descriptor
Wavelet frames
Equivalence classes
Graphic methods
Statistical methods
Wavelet analysis
Generalized gamma distribution
Kullback Leibler divergence
Retrieval performance
Rotation invariant
Statistical modeling
Texture descriptor
Von Mises distribution
Wavelet frame
Image retrieval
description This paper presents a texture descriptor based on wavelet frame transforms. At each position in the image, and for each resolution level, we consider both vertical and horizontal wavelet detail coefficients as the components of a bivariate random vector. The magnitudes and angles of these vectors are computed. At each level the empirical histogram of magnitudes is modeled by a Generalized Gamma distribution, and the empirical histogram of angles is modeled by a different version of the von Mises distribution that accounts for histograms with 2 modes. Each texture is characterized by few parameters. A new distance is presented (based on the Kullback-Leibler divergence) that allows giving relative importance to each model and to each resolution level. This distance is later conveniently adapted to provide for rotation invariance, by establishing equivalence classes over distributions of angles. Through a broad set of experiments on three different image databases, we demonstrate that our new descriptor and distance measure can be successfully applied in the context of texture retrieval. We compare our system to several relevant methods in this field in terms of retrieval performance and number of parameters used by each method. We also include some classification tests. In all the tests, we obtain superior retrieval rates for a set of fewer parameters involved. © 2014 Elsevier Ltd.
author Acevedo, Daniel G.
Ruedin, Ana María Clara
author_facet Acevedo, Daniel G.
Ruedin, Ana María Clara
author_sort Acevedo, Daniel G.
title A statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval
title_short A statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval
title_full A statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval
title_fullStr A statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval
title_full_unstemmed A statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval
title_sort statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval
publishDate 2014
url https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_00313203_v47_n9_p2925_DeVes
http://hdl.handle.net/20.500.12110/paper_00313203_v47_n9_p2925_DeVes
work_keys_str_mv AT acevedodanielg astatisticalmodelformagnitudesandanglesofwaveletframecoefficientsanditsapplicationtotextureretrieval
AT ruedinanamariaclara astatisticalmodelformagnitudesandanglesofwaveletframecoefficientsanditsapplicationtotextureretrieval
AT acevedodanielg statisticalmodelformagnitudesandanglesofwaveletframecoefficientsanditsapplicationtotextureretrieval
AT ruedinanamariaclara statisticalmodelformagnitudesandanglesofwaveletframecoefficientsanditsapplicationtotextureretrieval
_version_ 1768545728697729024

Ejemplares similares