Personal recognition using multi-angles gait sequences

Connie Tee, Michael Kah Ong Goh, Beng Jin Teoh

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

2 Citations (Scopus)

Abstract

This paper presents an automatic gait recognition system which recognizes a person by the way he/she walks. The gait signature is obtained based on the contour width information of the silhouette of a person. Using this statistical shape information, we could capture the compact structural and dynamic features of the walking pattern. As the extracted contour width feature is large in size, Fisher Discriminant Analysis is used to reduce the dimension of the feature set. After that, a modified Probabilistic Neural Networks is deployed to classify the reduced feature set. Satisfactory result could be achieved when we fused gait images from multiple viewing angles. In this research, we aim to identify the complete gait cycle of each subjects. Every person walks at difference paces and thus different numbers of frame sizes are required to record the walking pattern. As such, it is not robust and feasible if we take a fixed number of video frames to process the gait sequences for all subjects. We endeavor to find an efficient method to identify the complete gait cycle of each individual. In this case, we could work on succinct representation of the gait pattern which is invariant to walking speed for each individual.

Original languageEnglish
Title of host publicationDigital Information Processing and Communications - International Conference, ICDIPC 2011, Proceedings
Pages497-508
Number of pages12
EditionPART 2
DOIs
Publication statusPublished - 2011 Jul 19
EventInternational Conference on Digital Information Processing and Communications, ICDIPC 2011 - Ostrava, Czech Republic
Duration: 2011 Jul 72011 Jul 9

Publication series

NameCommunications in Computer and Information Science
NumberPART 2
Volume189 CCIS
ISSN (Print)1865-0929

Other

OtherInternational Conference on Digital Information Processing and Communications, ICDIPC 2011
CountryCzech Republic
CityOstrava
Period11/7/711/7/9

Fingerprint

Gait
Discriminant analysis
Neural networks
Angle
Person
Walk
Fisher Discriminant Analysis
Gait Recognition
Cycle
Probabilistic Neural Network
Silhouette
Signature
Classify
Invariant

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Cite this

Tee, C., Kah Ong Goh, M., & Teoh, B. J. (2011). Personal recognition using multi-angles gait sequences. In Digital Information Processing and Communications - International Conference, ICDIPC 2011, Proceedings (PART 2 ed., pp. 497-508). (Communications in Computer and Information Science; Vol. 189 CCIS, No. PART 2). https://doi.org/10.1007/978-3-642-22410-2_43
Tee, Connie ; Kah Ong Goh, Michael ; Teoh, Beng Jin. / Personal recognition using multi-angles gait sequences. Digital Information Processing and Communications - International Conference, ICDIPC 2011, Proceedings. PART 2. ed. 2011. pp. 497-508 (Communications in Computer and Information Science; PART 2).
@inproceedings{94e84c52266e409bb6aae8e2992907a3,
title = "Personal recognition using multi-angles gait sequences",
abstract = "This paper presents an automatic gait recognition system which recognizes a person by the way he/she walks. The gait signature is obtained based on the contour width information of the silhouette of a person. Using this statistical shape information, we could capture the compact structural and dynamic features of the walking pattern. As the extracted contour width feature is large in size, Fisher Discriminant Analysis is used to reduce the dimension of the feature set. After that, a modified Probabilistic Neural Networks is deployed to classify the reduced feature set. Satisfactory result could be achieved when we fused gait images from multiple viewing angles. In this research, we aim to identify the complete gait cycle of each subjects. Every person walks at difference paces and thus different numbers of frame sizes are required to record the walking pattern. As such, it is not robust and feasible if we take a fixed number of video frames to process the gait sequences for all subjects. We endeavor to find an efficient method to identify the complete gait cycle of each individual. In this case, we could work on succinct representation of the gait pattern which is invariant to walking speed for each individual.",
author = "Connie Tee and {Kah Ong Goh}, Michael and Teoh, {Beng Jin}",
year = "2011",
month = "7",
day = "19",
doi = "10.1007/978-3-642-22410-2_43",
language = "English",
isbn = "9783642224096",
series = "Communications in Computer and Information Science",
number = "PART 2",
pages = "497--508",
booktitle = "Digital Information Processing and Communications - International Conference, ICDIPC 2011, Proceedings",
edition = "PART 2",

}

Tee, C, Kah Ong Goh, M & Teoh, BJ 2011, Personal recognition using multi-angles gait sequences. in Digital Information Processing and Communications - International Conference, ICDIPC 2011, Proceedings. PART 2 edn, Communications in Computer and Information Science, no. PART 2, vol. 189 CCIS, pp. 497-508, International Conference on Digital Information Processing and Communications, ICDIPC 2011, Ostrava, Czech Republic, 11/7/7. https://doi.org/10.1007/978-3-642-22410-2_43

Personal recognition using multi-angles gait sequences. / Tee, Connie; Kah Ong Goh, Michael; Teoh, Beng Jin.

Digital Information Processing and Communications - International Conference, ICDIPC 2011, Proceedings. PART 2. ed. 2011. p. 497-508 (Communications in Computer and Information Science; Vol. 189 CCIS, No. PART 2).

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

TY - GEN

T1 - Personal recognition using multi-angles gait sequences

AU - Tee, Connie

AU - Kah Ong Goh, Michael

AU - Teoh, Beng Jin

PY - 2011/7/19

Y1 - 2011/7/19

N2 - This paper presents an automatic gait recognition system which recognizes a person by the way he/she walks. The gait signature is obtained based on the contour width information of the silhouette of a person. Using this statistical shape information, we could capture the compact structural and dynamic features of the walking pattern. As the extracted contour width feature is large in size, Fisher Discriminant Analysis is used to reduce the dimension of the feature set. After that, a modified Probabilistic Neural Networks is deployed to classify the reduced feature set. Satisfactory result could be achieved when we fused gait images from multiple viewing angles. In this research, we aim to identify the complete gait cycle of each subjects. Every person walks at difference paces and thus different numbers of frame sizes are required to record the walking pattern. As such, it is not robust and feasible if we take a fixed number of video frames to process the gait sequences for all subjects. We endeavor to find an efficient method to identify the complete gait cycle of each individual. In this case, we could work on succinct representation of the gait pattern which is invariant to walking speed for each individual.

AB - This paper presents an automatic gait recognition system which recognizes a person by the way he/she walks. The gait signature is obtained based on the contour width information of the silhouette of a person. Using this statistical shape information, we could capture the compact structural and dynamic features of the walking pattern. As the extracted contour width feature is large in size, Fisher Discriminant Analysis is used to reduce the dimension of the feature set. After that, a modified Probabilistic Neural Networks is deployed to classify the reduced feature set. Satisfactory result could be achieved when we fused gait images from multiple viewing angles. In this research, we aim to identify the complete gait cycle of each subjects. Every person walks at difference paces and thus different numbers of frame sizes are required to record the walking pattern. As such, it is not robust and feasible if we take a fixed number of video frames to process the gait sequences for all subjects. We endeavor to find an efficient method to identify the complete gait cycle of each individual. In this case, we could work on succinct representation of the gait pattern which is invariant to walking speed for each individual.

UR - http://www.scopus.com/inward/record.url?scp=79960304323&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960304323&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-22410-2_43

DO - 10.1007/978-3-642-22410-2_43

M3 - Conference contribution

SN - 9783642224096

T3 - Communications in Computer and Information Science

SP - 497

EP - 508

BT - Digital Information Processing and Communications - International Conference, ICDIPC 2011, Proceedings

ER -

Tee C, Kah Ong Goh M, Teoh BJ. Personal recognition using multi-angles gait sequences. In Digital Information Processing and Communications - International Conference, ICDIPC 2011, Proceedings. PART 2 ed. 2011. p. 497-508. (Communications in Computer and Information Science; PART 2). https://doi.org/10.1007/978-3-642-22410-2_43