RT Journal Article
A1 Daigo Muramatsu
AD The Institute of Scientific and Industrial Research, Osaka University, 8–1 Mihogaoka, Ibaraki, Osaka 567-0047, Japan
A1 Yasushi Makihara
AD The Institute of Scientific and Industrial Research, Osaka University, 8–1 Mihogaoka, Ibaraki, Osaka 567-0047, Japan
A1 Yasushi Yagi
AD The Institute of Scientific and Industrial Research, Osaka University, 8–1 Mihogaoka, Ibaraki, Osaka 567-0047, Japan

PB iet
T1 Cross-view gait recognition by fusion of multiple transformation consistency measures
JN IET Biometrics
VO 4
IS 2
SP 62
OP 73
AB Gait is a promising modality for forensic science because it has discrimination ability even if the gait features are extracted from low-quality image sequences captured at a distance. However, in forensic cases the observation view is often different, leading to accuracy degradation. Therefore the authors propose a gait recognition algorithm that achieves high accuracy in cases where observation views are different. They used a view transformation technique, and generated multiple joint gait features by changing the source gait features. They formed a hypothesis that the multiple transformed features and original features should be similar to each other if the target subjects are the same. They calculated multiple scores that measured the consistency of the features, and a likelihood ratio from the scores. To evaluate the accuracy of the proposed method, they drew Tippett plots and empirical cross-entropy plots, together with cumulative match characteristic curves and receiver operator characteristic curves, and evaluated discrimination ability and calibration quality. The results showed that their proposed method achieves good results in terms of discrimination and calibration.
K1 forensic science
K1 gait feature extraction
K1 calibration quality
K1 discrimination ability
K1 cross-view gait recognition
K1 transformation consistency measures
K1 gait recognition algorithm
K1 cumulative match characteristic curves
K1 Tippett plots
K1 empirical cross-entropy plots
K1 view transformation technique
K1 low-quality image sequences
K1 receiver operator characteristic curves
DO https://doi.org/10.1049/iet-bmt.2014.0042
UL https://digital-library.theiet.org/;jsessionid=2ackoajnir6ma.x-iet-live-01content/journals/10.1049/iet-bmt.2014.0042
LA English
SN 2047-4938
YR 2015
OL EN