Multi-view gait recognition fusion methodology

Imran Fareed Nizami, Sungjun Hong, Heesung Lee, Sungje Ahn, Kar Ann Toh, Euntai Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

This paper presents a multi-view gait recognition algorithm for identification at a distance. We make use of two well known and effective gait representations namely Motion Silhouette Image (MSI) and Gait Energy Image (GEI). MSI and GEI inherently capture the spatiotemporal characteristics of gait. We show that the individual recognition performance of MSI and GEI can be improved by using a fusion methodology. The features for MSI and GEI images are extracted using Independent Component Analysis (ICA) which is used widely in such applications. Extreme Learning Machine (ELM) classifier is then used for classification. ELM is a multiclass classifier which offers the advantage of less time consumption and high performance. The results are fused at score level making use of fusion rules such as min and max [17] to make the algorithm robust, reliable and to improve the performance of the system. Our approach is tested on the NLPR gait database. The NLPR gait database corresponds to 20 subjects, each subject has 4 sequences and there are 3 viewing angles (0°, 45° and 90°) for each person. The results on the dataset show that the fusion gives good performance for the 3 views considered in this paper.

Original languageEnglish
Title of host publication2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008
Pages2101-2105
Number of pages5
DOIs
Publication statusPublished - 2008 Sep 23
Event2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008 - Singapore, Singapore
Duration: 2008 Jun 32008 Jun 5

Publication series

Name2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008

Other

Other2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008
CountrySingapore
CitySingapore
Period08/6/308/6/5

Fingerprint

Fusion reactions
Learning systems
Classifiers
Independent component analysis

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

Nizami, I. F., Hong, S., Lee, H., Ahn, S., Toh, K. A., & Kim, E. (2008). Multi-view gait recognition fusion methodology. In 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008 (pp. 2101-2105). [4582890] (2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008). https://doi.org/10.1109/ICIEA.2008.4582890
Nizami, Imran Fareed ; Hong, Sungjun ; Lee, Heesung ; Ahn, Sungje ; Toh, Kar Ann ; Kim, Euntai. / Multi-view gait recognition fusion methodology. 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008. 2008. pp. 2101-2105 (2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008).
@inproceedings{0e34e0c2f52a40a584ef59b4ccc8ad71,
title = "Multi-view gait recognition fusion methodology",
abstract = "This paper presents a multi-view gait recognition algorithm for identification at a distance. We make use of two well known and effective gait representations namely Motion Silhouette Image (MSI) and Gait Energy Image (GEI). MSI and GEI inherently capture the spatiotemporal characteristics of gait. We show that the individual recognition performance of MSI and GEI can be improved by using a fusion methodology. The features for MSI and GEI images are extracted using Independent Component Analysis (ICA) which is used widely in such applications. Extreme Learning Machine (ELM) classifier is then used for classification. ELM is a multiclass classifier which offers the advantage of less time consumption and high performance. The results are fused at score level making use of fusion rules such as min and max [17] to make the algorithm robust, reliable and to improve the performance of the system. Our approach is tested on the NLPR gait database. The NLPR gait database corresponds to 20 subjects, each subject has 4 sequences and there are 3 viewing angles (0°, 45° and 90°) for each person. The results on the dataset show that the fusion gives good performance for the 3 views considered in this paper.",
author = "Nizami, {Imran Fareed} and Sungjun Hong and Heesung Lee and Sungje Ahn and Toh, {Kar Ann} and Euntai Kim",
year = "2008",
month = "9",
day = "23",
doi = "10.1109/ICIEA.2008.4582890",
language = "English",
isbn = "9781424417186",
series = "2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008",
pages = "2101--2105",
booktitle = "2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008",

}

Nizami, IF, Hong, S, Lee, H, Ahn, S, Toh, KA & Kim, E 2008, Multi-view gait recognition fusion methodology. in 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008., 4582890, 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008, pp. 2101-2105, 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008, Singapore, Singapore, 08/6/3. https://doi.org/10.1109/ICIEA.2008.4582890

Multi-view gait recognition fusion methodology. / Nizami, Imran Fareed; Hong, Sungjun; Lee, Heesung; Ahn, Sungje; Toh, Kar Ann; Kim, Euntai.

2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008. 2008. p. 2101-2105 4582890 (2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Multi-view gait recognition fusion methodology

AU - Nizami, Imran Fareed

AU - Hong, Sungjun

AU - Lee, Heesung

AU - Ahn, Sungje

AU - Toh, Kar Ann

AU - Kim, Euntai

PY - 2008/9/23

Y1 - 2008/9/23

N2 - This paper presents a multi-view gait recognition algorithm for identification at a distance. We make use of two well known and effective gait representations namely Motion Silhouette Image (MSI) and Gait Energy Image (GEI). MSI and GEI inherently capture the spatiotemporal characteristics of gait. We show that the individual recognition performance of MSI and GEI can be improved by using a fusion methodology. The features for MSI and GEI images are extracted using Independent Component Analysis (ICA) which is used widely in such applications. Extreme Learning Machine (ELM) classifier is then used for classification. ELM is a multiclass classifier which offers the advantage of less time consumption and high performance. The results are fused at score level making use of fusion rules such as min and max [17] to make the algorithm robust, reliable and to improve the performance of the system. Our approach is tested on the NLPR gait database. The NLPR gait database corresponds to 20 subjects, each subject has 4 sequences and there are 3 viewing angles (0°, 45° and 90°) for each person. The results on the dataset show that the fusion gives good performance for the 3 views considered in this paper.

AB - This paper presents a multi-view gait recognition algorithm for identification at a distance. We make use of two well known and effective gait representations namely Motion Silhouette Image (MSI) and Gait Energy Image (GEI). MSI and GEI inherently capture the spatiotemporal characteristics of gait. We show that the individual recognition performance of MSI and GEI can be improved by using a fusion methodology. The features for MSI and GEI images are extracted using Independent Component Analysis (ICA) which is used widely in such applications. Extreme Learning Machine (ELM) classifier is then used for classification. ELM is a multiclass classifier which offers the advantage of less time consumption and high performance. The results are fused at score level making use of fusion rules such as min and max [17] to make the algorithm robust, reliable and to improve the performance of the system. Our approach is tested on the NLPR gait database. The NLPR gait database corresponds to 20 subjects, each subject has 4 sequences and there are 3 viewing angles (0°, 45° and 90°) for each person. The results on the dataset show that the fusion gives good performance for the 3 views considered in this paper.

UR - http://www.scopus.com/inward/record.url?scp=51949105982&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51949105982&partnerID=8YFLogxK

U2 - 10.1109/ICIEA.2008.4582890

DO - 10.1109/ICIEA.2008.4582890

M3 - Conference contribution

AN - SCOPUS:51949105982

SN - 9781424417186

T3 - 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008

SP - 2101

EP - 2105

BT - 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008

ER -

Nizami IF, Hong S, Lee H, Ahn S, Toh KA, Kim E. Multi-view gait recognition fusion methodology. In 2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008. 2008. p. 2101-2105. 4582890. (2008 3rd IEEE Conference on Industrial Electronics and Applications, ICIEA 2008). https://doi.org/10.1109/ICIEA.2008.4582890