Building Recognition Based on Sparse Representation of Spatial Texture and Color Features
In this paper, we presented a novel building recognition method based on a sparse representation of spatial texture and color features. At present, the most popular methods are based on gist features, which can only roughly reflect the spatial information of building images. The proposed method, in...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8667827/ |
id |
doaj-4e3177591a6d4871bd4845ebbff2eaca |
---|---|
record_format |
Article |
spelling |
doaj-4e3177591a6d4871bd4845ebbff2eaca2021-03-29T22:10:55ZengIEEEIEEE Access2169-35362019-01-017372203722710.1109/ACCESS.2019.29053048667827Building Recognition Based on Sparse Representation of Spatial Texture and Color FeaturesBin Li0https://orcid.org/0000-0001-8268-0430Fuqiang Sun1Yonghan Zhang2School of Computer Science, Northeast Electric Power University, Jilin, ChinaSchool of Computer Science, Northeast Electric Power University, Jilin, ChinaSchool of Computer Science, Northeast Electric Power University, Jilin, ChinaIn this paper, we presented a novel building recognition method based on a sparse representation of spatial texture and color features. At present, the most popular methods are based on gist features, which can only roughly reflect the spatial information of building images. The proposed method, in contrast, uses multi-scale neighborhood sensitive histograms of oriented gradient (MNSHOGs) and color auto-correlogram (CA) to extract texture and color features of building images. Both the MNSHOG and the CA take spatial information of building images into account while calculating texture and color features. Then, color and texture features are combined to form joint features whose sparse representation can be dimensionally reduced by an autoencoder. Finally, an extreme learning machine is used to classify the combined features after dimensionality reduction into different classes. Several experiments were conducted on the benchmark Sheffield building dataset. The mean recognition rate of our method is much higher than that of the existing methods, which shows the effectiveness of our method.https://ieeexplore.ieee.org/document/8667827/Building recognitiontexture and color featuresextreme learning machineautoencoderSheffield buildings databasesparse representation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Bin Li Fuqiang Sun Yonghan Zhang |
spellingShingle |
Bin Li Fuqiang Sun Yonghan Zhang Building Recognition Based on Sparse Representation of Spatial Texture and Color Features IEEE Access Building recognition texture and color features extreme learning machine autoencoder Sheffield buildings database sparse representation |
author_facet |
Bin Li Fuqiang Sun Yonghan Zhang |
author_sort |
Bin Li |
title |
Building Recognition Based on Sparse Representation of Spatial Texture and Color Features |
title_short |
Building Recognition Based on Sparse Representation of Spatial Texture and Color Features |
title_full |
Building Recognition Based on Sparse Representation of Spatial Texture and Color Features |
title_fullStr |
Building Recognition Based on Sparse Representation of Spatial Texture and Color Features |
title_full_unstemmed |
Building Recognition Based on Sparse Representation of Spatial Texture and Color Features |
title_sort |
building recognition based on sparse representation of spatial texture and color features |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
In this paper, we presented a novel building recognition method based on a sparse representation of spatial texture and color features. At present, the most popular methods are based on gist features, which can only roughly reflect the spatial information of building images. The proposed method, in contrast, uses multi-scale neighborhood sensitive histograms of oriented gradient (MNSHOGs) and color auto-correlogram (CA) to extract texture and color features of building images. Both the MNSHOG and the CA take spatial information of building images into account while calculating texture and color features. Then, color and texture features are combined to form joint features whose sparse representation can be dimensionally reduced by an autoencoder. Finally, an extreme learning machine is used to classify the combined features after dimensionality reduction into different classes. Several experiments were conducted on the benchmark Sheffield building dataset. The mean recognition rate of our method is much higher than that of the existing methods, which shows the effectiveness of our method. |
topic |
Building recognition texture and color features extreme learning machine autoencoder Sheffield buildings database sparse representation |
url |
https://ieeexplore.ieee.org/document/8667827/ |
work_keys_str_mv |
AT binli buildingrecognitionbasedonsparserepresentationofspatialtextureandcolorfeatures AT fuqiangsun buildingrecognitionbasedonsparserepresentationofspatialtextureandcolorfeatures AT yonghanzhang buildingrecognitionbasedonsparserepresentationofspatialtextureandcolorfeatures |
_version_ |
1724192053573713920 |