TY - GEN
T1 - A hybrid approach for gait based gender classification using GEI and spatio temporal parameters
AU - Choudhary, Sneha
AU - Prakash, Chandra
AU - Kumar, Rajesh
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/11/30
Y1 - 2017/11/30
N2 - Gender classification play a significant role in recognition performance. For the purpose of visual surveillance, gender is considered as an important factor. In this paper a hybrid approach is proposed by fusing Gait Energy Image (GEI) with spatio temporal parameters for the gender classification. The dataset used is CASIA B which comprises of 118 subjects (89 males and 29 females). The proposed method consists of four steps. Gait Energy Image (GEI) is obtained by normalizing and averaging all the silhouette images in one gait cycle for all the subjects. The dimensions of GEI image is reduced by using principal component analysis. 5 spatio temporal parameters namely cadence, speed, height, stride length, stance period are calculated and concatenated with the reduced GEI Image. The reduced feature vector set is trained and tested using support vector machine and artificial neural network. Maximum accuracy achieved is 98.16% which shows the highly competitive results compared to previous methods.
AB - Gender classification play a significant role in recognition performance. For the purpose of visual surveillance, gender is considered as an important factor. In this paper a hybrid approach is proposed by fusing Gait Energy Image (GEI) with spatio temporal parameters for the gender classification. The dataset used is CASIA B which comprises of 118 subjects (89 males and 29 females). The proposed method consists of four steps. Gait Energy Image (GEI) is obtained by normalizing and averaging all the silhouette images in one gait cycle for all the subjects. The dimensions of GEI image is reduced by using principal component analysis. 5 spatio temporal parameters namely cadence, speed, height, stride length, stance period are calculated and concatenated with the reduced GEI Image. The reduced feature vector set is trained and tested using support vector machine and artificial neural network. Maximum accuracy achieved is 98.16% which shows the highly competitive results compared to previous methods.
KW - Gait eenergy image
KW - Gender identification
KW - PCA
KW - Spatio temporal parameters
UR - http://www.scopus.com/inward/record.url?scp=85042650352&partnerID=8YFLogxK
U2 - 10.1109/ICACCI.2017.8126100
DO - 10.1109/ICACCI.2017.8126100
M3 - Conference contribution
AN - SCOPUS:85042650352
T3 - 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017
SP - 1767
EP - 1771
BT - 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017
Y2 - 13 September 2017 through 16 September 2017
ER -