Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal Images
In this paper, we propose a bimodal 3D facial recognition method aimed at increasing the recognition rate and reducing the effect of illumination, pose, expression, ages, and occlusion on facial recognition. There are two features extracted from the multiscale sub-blocks in both the 3D mode depth ma...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-02-01
|
Series: | Information |
Subjects: | |
Online Access: | http://www.mdpi.com/2078-2489/9/3/48 |
id |
doaj-490b09e3fc974428937bb0e7fc006c50 |
---|---|
record_format |
Article |
spelling |
doaj-490b09e3fc974428937bb0e7fc006c502020-11-24T22:22:15ZengMDPI AGInformation2078-24892018-02-01934810.3390/info9030048info9030048Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal ImagesYingchun Guo0Ruoyu Wei1Yi Liu2School of Computer Science and Engineering, Hebei University of Technology, Tianjin 300400, ChinaSchool of Computer Science and Engineering, Hebei University of Technology, Tianjin 300400, ChinaSchool of Computer Science and Engineering, Hebei University of Technology, Tianjin 300400, ChinaIn this paper, we propose a bimodal 3D facial recognition method aimed at increasing the recognition rate and reducing the effect of illumination, pose, expression, ages, and occlusion on facial recognition. There are two features extracted from the multiscale sub-blocks in both the 3D mode depth map and 2D mode intensity map, which are the local gradient pattern (LGP) feature and the weighted histogram of gradient orientation (WHGO) feature. LGP and WHGO features are cascaded to form the 3D facial feature vector LGP-WHGO, and are further trained and identified by the support vector machine (SVM). Experiments on the CASIA database, FRGC v2.0 database, and Bosphorus database show that, the proposed method can efficiently extract the structure information and texture information of the facial image, and have a robustness to illumination, expression, occlusion and pose.http://www.mdpi.com/2078-2489/9/3/483D face recognitiondepth mapintensity mapLGP-WHGOmultiscale sub-blocksbimodal |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yingchun Guo Ruoyu Wei Yi Liu |
spellingShingle |
Yingchun Guo Ruoyu Wei Yi Liu Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal Images Information 3D face recognition depth map intensity map LGP-WHGO multiscale sub-blocks bimodal |
author_facet |
Yingchun Guo Ruoyu Wei Yi Liu |
author_sort |
Yingchun Guo |
title |
Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal Images |
title_short |
Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal Images |
title_full |
Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal Images |
title_fullStr |
Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal Images |
title_full_unstemmed |
Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal Images |
title_sort |
weighted gradient feature extraction based on multiscale sub-blocks for 3d facial recognition in bimodal images |
publisher |
MDPI AG |
series |
Information |
issn |
2078-2489 |
publishDate |
2018-02-01 |
description |
In this paper, we propose a bimodal 3D facial recognition method aimed at increasing the recognition rate and reducing the effect of illumination, pose, expression, ages, and occlusion on facial recognition. There are two features extracted from the multiscale sub-blocks in both the 3D mode depth map and 2D mode intensity map, which are the local gradient pattern (LGP) feature and the weighted histogram of gradient orientation (WHGO) feature. LGP and WHGO features are cascaded to form the 3D facial feature vector LGP-WHGO, and are further trained and identified by the support vector machine (SVM). Experiments on the CASIA database, FRGC v2.0 database, and Bosphorus database show that, the proposed method can efficiently extract the structure information and texture information of the facial image, and have a robustness to illumination, expression, occlusion and pose. |
topic |
3D face recognition depth map intensity map LGP-WHGO multiscale sub-blocks bimodal |
url |
http://www.mdpi.com/2078-2489/9/3/48 |
work_keys_str_mv |
AT yingchunguo weightedgradientfeatureextractionbasedonmultiscalesubblocksfor3dfacialrecognitioninbimodalimages AT ruoyuwei weightedgradientfeatureextractionbasedonmultiscalesubblocksfor3dfacialrecognitioninbimodalimages AT yiliu weightedgradientfeatureextractionbasedonmultiscalesubblocksfor3dfacialrecognitioninbimodalimages |
_version_ |
1725769179385036800 |