Cargando…

Considering the Spatial Layout Information of Bag of Features (BoF) Framework for Image Classification

The spatial pooling method such as spatial pyramid matching (SPM) is very crucial in the bag of features model used in image classification. SPM partitions the image into a set of regular grids and assumes that the spatial layout of all visual words obey the uniform distribution over these regular g...

Descripción completa

Detalles Bibliográficos
Autores principales: Mu, Guangyu, Liu, Ying, Wang, Limin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4488279/
https://www.ncbi.nlm.nih.gov/pubmed/26121038
http://dx.doi.org/10.1371/journal.pone.0131164
_version_ 1782379123555958784
author Mu, Guangyu
Liu, Ying
Wang, Limin
author_facet Mu, Guangyu
Liu, Ying
Wang, Limin
author_sort Mu, Guangyu
collection PubMed
description The spatial pooling method such as spatial pyramid matching (SPM) is very crucial in the bag of features model used in image classification. SPM partitions the image into a set of regular grids and assumes that the spatial layout of all visual words obey the uniform distribution over these regular grids. However, in practice, we consider that different visual words should obey different spatial layout distributions. To improve SPM, we develop a novel spatial pooling method, namely spatial distribution pooling (SDP). The proposed SDP method uses an extension model of Gauss mixture model to estimate the spatial layout distributions of the visual vocabulary. For each visual word type, SDP can generate a set of flexible grids rather than the regular grids from the traditional SPM. Furthermore, we can compute the grid weights for visual word tokens according to their spatial coordinates. The experimental results demonstrate that SDP outperforms the traditional spatial pooling methods, and is competitive with the state-of-the-art classification accuracy on several challenging image datasets.
format Online
Article
Text
id pubmed-4488279
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-44882792015-07-02 Considering the Spatial Layout Information of Bag of Features (BoF) Framework for Image Classification Mu, Guangyu Liu, Ying Wang, Limin PLoS One Research Article The spatial pooling method such as spatial pyramid matching (SPM) is very crucial in the bag of features model used in image classification. SPM partitions the image into a set of regular grids and assumes that the spatial layout of all visual words obey the uniform distribution over these regular grids. However, in practice, we consider that different visual words should obey different spatial layout distributions. To improve SPM, we develop a novel spatial pooling method, namely spatial distribution pooling (SDP). The proposed SDP method uses an extension model of Gauss mixture model to estimate the spatial layout distributions of the visual vocabulary. For each visual word type, SDP can generate a set of flexible grids rather than the regular grids from the traditional SPM. Furthermore, we can compute the grid weights for visual word tokens according to their spatial coordinates. The experimental results demonstrate that SDP outperforms the traditional spatial pooling methods, and is competitive with the state-of-the-art classification accuracy on several challenging image datasets. Public Library of Science 2015-06-29 /pmc/articles/PMC4488279/ /pubmed/26121038 http://dx.doi.org/10.1371/journal.pone.0131164 Text en © 2015 Mu et al http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.
spellingShingle Research Article
Mu, Guangyu
Liu, Ying
Wang, Limin
Considering the Spatial Layout Information of Bag of Features (BoF) Framework for Image Classification
title Considering the Spatial Layout Information of Bag of Features (BoF) Framework for Image Classification
title_full Considering the Spatial Layout Information of Bag of Features (BoF) Framework for Image Classification
title_fullStr Considering the Spatial Layout Information of Bag of Features (BoF) Framework for Image Classification
title_full_unstemmed Considering the Spatial Layout Information of Bag of Features (BoF) Framework for Image Classification
title_short Considering the Spatial Layout Information of Bag of Features (BoF) Framework for Image Classification
title_sort considering the spatial layout information of bag of features (bof) framework for image classification
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4488279/
https://www.ncbi.nlm.nih.gov/pubmed/26121038
http://dx.doi.org/10.1371/journal.pone.0131164
work_keys_str_mv AT muguangyu consideringthespatiallayoutinformationofbagoffeaturesbofframeworkforimageclassification
AT liuying consideringthespatiallayoutinformationofbagoffeaturesbofframeworkforimageclassification
AT wanglimin consideringthespatiallayoutinformationofbagoffeaturesbofframeworkforimageclassification