Sparse graph based deep learning networks for face recognition

Renjie Wu, Seiichiro Kamata

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In recent years, deep learning based approaches have substantially improved the performance of face recognition. Most existing deep learning techniques work well, but neglect effective utilization of face correlation information. The resulting performance loss is noteworthy for personal appearance variations caused by factors such as illumination, pose, occlusion, and misalignment. We believe that face correlation information should be introduced to solve this network performance problem originating from by intra-personal variations. Recently, graph deep learning approaches have emerged for representing structured graph data. A graph is a powerful tool for representing complex information of the face image. In this paper, we survey the recent research related to the graph structure of Convolutional Neural Networks and try to devise a definition of graph structure included in Compressed Sensing and Deep Learning. This paper devoted to the story explain of two properties of our graph-sparse and depth. Sparse can be advantageous since features are more likely to be linearly separable and they are more robust. The depth means that this is a multi-resolution multi-channel learning process. We think that sparse graph based deep neural network can more effectively make similar objects to attract each other, the relative, different objects mutually exclusive, similar to a better sparse multi-resolution clustering. Based on this concept. We propose a sparse graph representation based on the face correlation information that is embedded via the sparse reconstruction and deep learning within an irregular domain. The resulting classification is remarkably robust. The proposed method achieves high recognition rates of 99.61%(94.67%) on the benchmark LFW (YTF) facial evaluation database.

Original languageEnglish
Pages (from-to)2209-2219
Number of pages11
JournalIEICE Transactions on Information and Systems
VolumeE101D
Issue number9
DOIs
Publication statusPublished - 2018 Sep 1

Fingerprint

Face recognition
Compressed sensing
Network performance
Lighting
Deep learning
Neural networks

Keywords

  • Atom decomposition
  • Deep learning network
  • Face recognition
  • Sparse graph reconstruction

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

Sparse graph based deep learning networks for face recognition. / Wu, Renjie; Kamata, Seiichiro.

In: IEICE Transactions on Information and Systems, Vol. E101D, No. 9, 01.09.2018, p. 2209-2219.

Research output: Contribution to journalArticle

@article{9412a1ce555a485abebbc7781539a1ca,
title = "Sparse graph based deep learning networks for face recognition",
abstract = "In recent years, deep learning based approaches have substantially improved the performance of face recognition. Most existing deep learning techniques work well, but neglect effective utilization of face correlation information. The resulting performance loss is noteworthy for personal appearance variations caused by factors such as illumination, pose, occlusion, and misalignment. We believe that face correlation information should be introduced to solve this network performance problem originating from by intra-personal variations. Recently, graph deep learning approaches have emerged for representing structured graph data. A graph is a powerful tool for representing complex information of the face image. In this paper, we survey the recent research related to the graph structure of Convolutional Neural Networks and try to devise a definition of graph structure included in Compressed Sensing and Deep Learning. This paper devoted to the story explain of two properties of our graph-sparse and depth. Sparse can be advantageous since features are more likely to be linearly separable and they are more robust. The depth means that this is a multi-resolution multi-channel learning process. We think that sparse graph based deep neural network can more effectively make similar objects to attract each other, the relative, different objects mutually exclusive, similar to a better sparse multi-resolution clustering. Based on this concept. We propose a sparse graph representation based on the face correlation information that is embedded via the sparse reconstruction and deep learning within an irregular domain. The resulting classification is remarkably robust. The proposed method achieves high recognition rates of 99.61{\%}(94.67{\%}) on the benchmark LFW (YTF) facial evaluation database.",
keywords = "Atom decomposition, Deep learning network, Face recognition, Sparse graph reconstruction",
author = "Renjie Wu and Seiichiro Kamata",
year = "2018",
month = "9",
day = "1",
doi = "10.1587/transinf.2017PCP0012",
language = "English",
volume = "E101D",
pages = "2209--2219",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "9",

}

TY - JOUR

T1 - Sparse graph based deep learning networks for face recognition

AU - Wu, Renjie

AU - Kamata, Seiichiro

PY - 2018/9/1

Y1 - 2018/9/1

N2 - In recent years, deep learning based approaches have substantially improved the performance of face recognition. Most existing deep learning techniques work well, but neglect effective utilization of face correlation information. The resulting performance loss is noteworthy for personal appearance variations caused by factors such as illumination, pose, occlusion, and misalignment. We believe that face correlation information should be introduced to solve this network performance problem originating from by intra-personal variations. Recently, graph deep learning approaches have emerged for representing structured graph data. A graph is a powerful tool for representing complex information of the face image. In this paper, we survey the recent research related to the graph structure of Convolutional Neural Networks and try to devise a definition of graph structure included in Compressed Sensing and Deep Learning. This paper devoted to the story explain of two properties of our graph-sparse and depth. Sparse can be advantageous since features are more likely to be linearly separable and they are more robust. The depth means that this is a multi-resolution multi-channel learning process. We think that sparse graph based deep neural network can more effectively make similar objects to attract each other, the relative, different objects mutually exclusive, similar to a better sparse multi-resolution clustering. Based on this concept. We propose a sparse graph representation based on the face correlation information that is embedded via the sparse reconstruction and deep learning within an irregular domain. The resulting classification is remarkably robust. The proposed method achieves high recognition rates of 99.61%(94.67%) on the benchmark LFW (YTF) facial evaluation database.

AB - In recent years, deep learning based approaches have substantially improved the performance of face recognition. Most existing deep learning techniques work well, but neglect effective utilization of face correlation information. The resulting performance loss is noteworthy for personal appearance variations caused by factors such as illumination, pose, occlusion, and misalignment. We believe that face correlation information should be introduced to solve this network performance problem originating from by intra-personal variations. Recently, graph deep learning approaches have emerged for representing structured graph data. A graph is a powerful tool for representing complex information of the face image. In this paper, we survey the recent research related to the graph structure of Convolutional Neural Networks and try to devise a definition of graph structure included in Compressed Sensing and Deep Learning. This paper devoted to the story explain of two properties of our graph-sparse and depth. Sparse can be advantageous since features are more likely to be linearly separable and they are more robust. The depth means that this is a multi-resolution multi-channel learning process. We think that sparse graph based deep neural network can more effectively make similar objects to attract each other, the relative, different objects mutually exclusive, similar to a better sparse multi-resolution clustering. Based on this concept. We propose a sparse graph representation based on the face correlation information that is embedded via the sparse reconstruction and deep learning within an irregular domain. The resulting classification is remarkably robust. The proposed method achieves high recognition rates of 99.61%(94.67%) on the benchmark LFW (YTF) facial evaluation database.

KW - Atom decomposition

KW - Deep learning network

KW - Face recognition

KW - Sparse graph reconstruction

UR - http://www.scopus.com/inward/record.url?scp=85053828199&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053828199&partnerID=8YFLogxK

U2 - 10.1587/transinf.2017PCP0012

DO - 10.1587/transinf.2017PCP0012

M3 - Article

AN - SCOPUS:85053828199

VL - E101D

SP - 2209

EP - 2219

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 9

ER -