Feature selection gait-based gender classification under different circumstances

Sabir, Azhin Tahir; Al-Jawad, Naseer; Jassim, Sabah

doi:10.1117/12.2052586

Cited by 1 publication

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the process of comparison, we selected those methods that proposed gender classification in the neutral and non-neutral case and used CASIA B gait database. The comparison shows that our scheme outperforms the two other schemes with one exception (CW case in (16) ). VGEnEI and AVGEnEI).…”

Section: Resultsmentioning

confidence: 85%

“…The authors of (15) and (16) addressed external factor challenges by investigating the problem of two variations: clothing (coats wearing) and carrying bag con-dition in addition to the normal gait sequence. In (15) a hierarchy approach proposed for gender classification based on human gait.…”

Section: Related Workmentioning

confidence: 99%

“…In (16) three different sets of the feature are proposed based on wavelet transform the first called Spatio-temporal distance that extracted based on thedistance of the human body parts (like feet, knees, hand, Human Height and shoulder). The other two sets of feature extracted based on LL and non-LL subbands.…”

Section: Related Workmentioning

confidence: 99%

“…In this paper we aim to propose gait-based gender classification and we will address the same challeges as investigated in (15) and (16) (carrying bag and coat wearing gait sequences as addition to using neutral (normal) gait sequences), Moreover, a new feature set will be generated base on GEI and Gait Entropy Image (GEnI) called GEnEI.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Human gait-based gender classification using neutral and non-neutral gait sequences

Mawlood

Sabir

2019

innovaciencia

View full text Add to dashboard Cite

A biometric system offers automatic identification of an individual basedon characteristic possessed by the individual. Biometric identification systems are often categorized as physiological or behavioural characteristics.Gait as one of the behavioural biometric recognition aims to recognizean individual by the way he/she walk. In this paper we propose genderclassification based on human gait features using wavelet transform andinvestigates the problem of non-neutral gait sequences; Coat Wearing andcarrying bag condition as addition to the neutral gait sequences. We shallinvestigate a new set of feature that generated based on the Gait Energy Image and Gait Entropy Image called Gait Entropy Energy Image(GEnEI). Three different feature sets constructed from GEnEI basedon wavelet transform called, Approximation coefficient Gait EntropyEnergy Image, Vertical coefficient Gait Entropy Energy Image and Approximation & Vertical coefficients Gait Entropy Energy Image Finallytwo different classification methods are used to test the performance ofthe proposed method separately, called k-nearest-neighbour and SupportVector Machine. Our tests are based on a large number of experimentsusing a well-known gait database called CASIA B gait database, includes124 subjects (93 males and 31 females). The experimental result indicatesthat the proposed method provides significant results and outperform thestate of the art.

show abstract

Section: Resultsmentioning

confidence: 85%