Dimension Reduction Using Samples’ Inner Structure Based Graph for Face Recognition

Bin Li, Wei Pang, Yuhao Liu, Xiangchun Yu, Anan Du, Zhezhou Yu (Corresponding Author)

Research output: Contribution to journalArticle

1 Citation (Scopus)
4 Downloads (Pure)

Abstract

Graph construction plays a vital role in improving the performance of graph-based dimension reduction (DR) algorithms. In this paper, we propose a novel graph construction method, and we name the graph constructed from such method as samples’ inner structure based graph (SISG). Instead of determining the -nearest neighbors of each sample by calculating the Euclidean distance between vectorized sample pairs, our new method employs the newly defined sample similarities to calculate the neighbors of each sample, and the newly defined sample similarities are based on the samples’ inner structure information. The SISG not only reveals the inner structure information of the original sample matrix, but also avoids predefining the parameter as used in the -nearest neighbor method. In order to demonstrate the effectiveness of SISG, we apply it to an unsupervised DR algorithm, locality preserving projection (LPP). Experimental results on several benchmark face databases verify the feasibility and effectiveness of SISG.
Original languageEnglish
Article number603025
Number of pages11
JournalMathematical Problems in Engineering
Volume2014
DOIs
Publication statusPublished - 3 Jul 2014

Fingerprint

Dimension Reduction
Face recognition
Face Recognition
Graph in graph theory
Information Structure
Nearest Neighbor Method
Euclidean Distance
Locality
Nearest Neighbor
Projection
Face
Benchmark
Verify
Calculate

Keywords

  • dimensionality reduction
  • graph construction
  • graph embedding
  • samples' inner structure

Cite this

Dimension Reduction Using Samples’ Inner Structure Based Graph for Face Recognition. / Li, Bin; Pang, Wei; Liu, Yuhao; Yu, Xiangchun; Du, Anan; Yu, Zhezhou (Corresponding Author).

In: Mathematical Problems in Engineering, Vol. 2014, 603025, 03.07.2014.

Research output: Contribution to journalArticle

Li, Bin ; Pang, Wei ; Liu, Yuhao ; Yu, Xiangchun ; Du, Anan ; Yu, Zhezhou. / Dimension Reduction Using Samples’ Inner Structure Based Graph for Face Recognition. In: Mathematical Problems in Engineering. 2014 ; Vol. 2014.
@article{8fb3d81037854850862dc444e30dd7b5,
title = "Dimension Reduction Using Samples’ Inner Structure Based Graph for Face Recognition",
abstract = "Graph construction plays a vital role in improving the performance of graph-based dimension reduction (DR) algorithms. In this paper, we propose a novel graph construction method, and we name the graph constructed from such method as samples’ inner structure based graph (SISG). Instead of determining the -nearest neighbors of each sample by calculating the Euclidean distance between vectorized sample pairs, our new method employs the newly defined sample similarities to calculate the neighbors of each sample, and the newly defined sample similarities are based on the samples’ inner structure information. The SISG not only reveals the inner structure information of the original sample matrix, but also avoids predefining the parameter as used in the -nearest neighbor method. In order to demonstrate the effectiveness of SISG, we apply it to an unsupervised DR algorithm, locality preserving projection (LPP). Experimental results on several benchmark face databases verify the feasibility and effectiveness of SISG.",
keywords = "dimensionality reduction, graph construction, graph embedding, samples' inner structure",
author = "Bin Li and Wei Pang and Yuhao Liu and Xiangchun Yu and Anan Du and Zhezhou Yu",
note = "Acknowledgments This research is supported by (1) the Ph.D. Programs Foundation of Ministry of Education of China under Grant (no. 20120061110045) and (2) the Natural Science Foundation of Jilin Province of China under Grant (no. 201115022).",
year = "2014",
month = "7",
day = "3",
doi = "10.1155/2014/603025",
language = "English",
volume = "2014",
journal = "Mathematical Problems in Engineering",
issn = "1024-123X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Dimension Reduction Using Samples’ Inner Structure Based Graph for Face Recognition

AU - Li, Bin

AU - Pang, Wei

AU - Liu, Yuhao

AU - Yu, Xiangchun

AU - Du, Anan

AU - Yu, Zhezhou

N1 - Acknowledgments This research is supported by (1) the Ph.D. Programs Foundation of Ministry of Education of China under Grant (no. 20120061110045) and (2) the Natural Science Foundation of Jilin Province of China under Grant (no. 201115022).

PY - 2014/7/3

Y1 - 2014/7/3

N2 - Graph construction plays a vital role in improving the performance of graph-based dimension reduction (DR) algorithms. In this paper, we propose a novel graph construction method, and we name the graph constructed from such method as samples’ inner structure based graph (SISG). Instead of determining the -nearest neighbors of each sample by calculating the Euclidean distance between vectorized sample pairs, our new method employs the newly defined sample similarities to calculate the neighbors of each sample, and the newly defined sample similarities are based on the samples’ inner structure information. The SISG not only reveals the inner structure information of the original sample matrix, but also avoids predefining the parameter as used in the -nearest neighbor method. In order to demonstrate the effectiveness of SISG, we apply it to an unsupervised DR algorithm, locality preserving projection (LPP). Experimental results on several benchmark face databases verify the feasibility and effectiveness of SISG.

AB - Graph construction plays a vital role in improving the performance of graph-based dimension reduction (DR) algorithms. In this paper, we propose a novel graph construction method, and we name the graph constructed from such method as samples’ inner structure based graph (SISG). Instead of determining the -nearest neighbors of each sample by calculating the Euclidean distance between vectorized sample pairs, our new method employs the newly defined sample similarities to calculate the neighbors of each sample, and the newly defined sample similarities are based on the samples’ inner structure information. The SISG not only reveals the inner structure information of the original sample matrix, but also avoids predefining the parameter as used in the -nearest neighbor method. In order to demonstrate the effectiveness of SISG, we apply it to an unsupervised DR algorithm, locality preserving projection (LPP). Experimental results on several benchmark face databases verify the feasibility and effectiveness of SISG.

KW - dimensionality reduction

KW - graph construction

KW - graph embedding

KW - samples' inner structure

U2 - 10.1155/2014/603025

DO - 10.1155/2014/603025

M3 - Article

VL - 2014

JO - Mathematical Problems in Engineering

JF - Mathematical Problems in Engineering

SN - 1024-123X

M1 - 603025

ER -