AUTOMATIC DOOR OPENING USING GAIT IDENTIFICATION FOR MOVEMENT AS GESTURE

Abstract

A wide variety of organizations are using automated
person identification systems to improve Customer
satisfaction, operating efficiency as well as to secure
critical resources. Gait identification provides a way
to automatic person identification at distance in visual
surveillance and monitor people without their
cooperation. Controlled environments such as banks,
military installations and even airports need to be
able to quickly detect threats and provide differing
levels of access to different user groups. Gait shows a
particular way or manner of moving on foot and gait
recognition is the process of identifying an individual
by the manner in which they walk. Gait is less
unobtrusive biometric, which offers the possibility to
identify people at a distance, without any interaction or
co-operation from the subject; this is the property
which makes it so attractive. This paper proposed
new method for gait recognition. In this thesis, first
step is extraction of foreground objects i.e. human
and other moving objects from input video sequences or
binary silhouette of a walking person is detected from
each frame and human detection and tracking will be
performed. After getting binary silhouettes of human
beings model based approach is used to extract
the gait features of a person. This paper proposes
a uncorrelated multilinear discriminant analysis
(UMLDA) algorithm for the challenging problem
of gait recognition. At last neural network for matlab
tool is used for training and testing purpose. We
have created different model of neural network based
on hidden layer, selection of training algorithm and
setting the different parameter for training. And
then we will test for the combination of NN+SVM,
Knearest neighbour classification. Here all experiments
are done on gait database and input video. Here
all experiments are done on CASIA gait database.
Different groups of training and testing dataset give
different results. The best recognition result for our
method is 96.32%.