MA YINGLIANG

1
Hand and Gait Recognition
YingLiang Ma University of Glasgow
MA YINGLIANG
2
Hand Recognition by Using B-Spline Curves
MA YINGLIANG
3
Rigid Registration
MA YINGLIANG
4
Point projection for difference computation
Ma Y.L., and Hewitt W.T., Point inversion and
projection for NURBS curve and surface control
polygon approach, Computer Aided Geometric
Design, 20(2), pp.79-99, (2003). Ma Y.L.,
Pollick F.E. and Hewitt W. T., "Using B-Spline
Curves for Hand Recognition", In proceedings of
International conference of Pattern recognition,
Vol 3, pp. 274-277, (2004).
MA YINGLIANG
5
Gait Recognition by Using Cyclograms
Southampton Video database
Our motion capture database Ma Y.L., Paterson
H.M., Tao Y.G., Pollick F.E.,"A motion-capture
library for the study of identity, gender and
emotion perception from biological motion",
Behavior Research Methods, Instruments,
Computers, (in press).
MA YINGLIANG
6
Extract Cyclograms from Video data
MA YINGLIANG
7
Cyclograms
Basic Features
Feature Points
Feature Angles
 
MA YINGLIANG
8
Point projection for evaluating shape differences
Before Alignment
Point coincidence
Rotation Alignment
MA YINGLIANG
9
Recognition
k-nearest neighbour (KNN) classifier
MA YINGLIANG
10
Clustering
MA YINGLIANG
11
Recognition rate for Southampton database
KNN Classifier The test database contains 6 gait
samples from 10 individuals.
MA YINGLIANG
12
Recognition rate for our database
KNN Classifier The test database contains 4 gait
samples from 24 individuals (half males and half
females).
MA YINGLIANG