Person Identification in Surveillance video using gait biometric cues

Emdad Hossain, Girija Chetty

Research output: A Conference proceeding or a Chapter in BookConference contribution

4 Citations (Scopus)

Abstract

In this paper, we proposed a novel approach for establishing person identity based on gait cues in surveillance videos using simple feature extraction and classifier methods. Person identity verification is an exigent task. When we go for identification or verification, first thing we count; the process or the method. Robust identification always depends on trait selection and robust method. From the beginning of the automated identification; classifiers and specific trait was the main concern, because, classifier is the tool which enables scientists to identity a person or classify a person in respect to provided input, on the other hand, biometric trait has to be unique, reliable and should have expected applicability. We used classifier approaches based on two different classifiers-NaiveBayes and C4.5 [1]
Original languageEnglish
Title of host publication2012 International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1877-1881
Number of pages5
ISBN (Electronic)9781467300247
ISBN (Print)9781467300254
DOIs
Publication statusPublished - 29 May 2012
EventFSKD 2012, International Conference on Fuzzy Systems and Knowledge Discovery - Chonqing, Chonqing, China
Duration: 29 May 201231 May 2012

Conference

ConferenceFSKD 2012, International Conference on Fuzzy Systems and Knowledge Discovery
CountryChina
CityChonqing
Period29/05/1231/05/12

Fingerprint Dive into the research topics of 'Person Identification in Surveillance video using gait biometric cues'. Together they form a unique fingerprint.

  • Cite this

    Hossain, E., & Chetty, G. (2012). Person Identification in Surveillance video using gait biometric cues. In 2012 International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) (pp. 1877-1881). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/FSKD.2012.6234146