Human Gait Recognition Using Gaussian Membership Function

Pratibha Mishra Shweta EzraSamrat Ashok Technological Institute Dhar polytechnic collegeVidisha, (M.P.) India Dhar (M.P.) IndiaMpratibha9@gmail.com shwetaezra@gmail.com Pratibha_mishra_satna@yahoo.co.in

Abstract- Human gait is a spatio-temporal phenomenon and typifies the motion characteristics of an individual. The gait of a person is easily recognizable when extracted from side view of the person. Accordingly, gait-recognition algorithms work best when presented with images where the person walks parallel to the camera (i.e. the image plane). Gait Recognition refers to identification of an individual based on the style of walking. This paper proposed a new algorithm which is based on Gaussian membership function. The Gaussian Membership function was chosen because of its popularity and simplicity. Gaussian membership functions are generated according to person’s walk and recognition is achieved by matching the curves by calculating the mean and variance, and used for recognition. Only the side-view of the person is considered, since this viewing angle provide the richest information of the gait of the waking person.

Keywords- Gait recognition; Biometrics; Gaussian membership function ; Control points; Database; Mean; Variance.

1. INTRODUCTION

Gait recognition is a kind of biometrics using the manner of walking to recognize an individual. More formal definition of biometrics is given by [1], “Gait recognition refers to automatic identification of an individual based on the style of walking”.Gait is treated as a sequence of holistic binary patterns Gait recognition Approaches can be broadly categorized into the model-based approach, where human body structure is explicitly modeled, and the model-free approach, where (silhouettes). Many studies have now shown that it is possible to recognize people by the way they walk. It is well-known that biometrics is a powerful tool for reliable automated person identification, but at present, none of the conventional biometrics like fingerprints recognition.

Iris recognition can work well from a large distance. In visual surveillance, the distances between the cameras and the people under surveillance are often large. In these situations, it is almost impossible to acquire the detailed conventional biometric information. Unlike other biometrics, gait can be

captured from a distant camera, without drawing the attention of the observed subject.

The performance of image-based gait recognition is not very good because Features extracted from image sequences have a little difference with the original information included in the gait. There is no efficient algorithm proposed yet to minimize the difference between the three dimensional information and features extracted from projected images [3].

2. RELATED WORKS

Chan-Su Lee [7] presented an approach “Identification of people using silhouette gait image”. He used a bilinear model to separate two independent factors, gait style and phase. N-normalized gait poses is defined and generated by embedding gait image sequences to a standard lower dimensional manifold and learning mapping from the manifold to every pixel. This normalized gait phase is used to collect aligned gait poses from different speed walking image sequence. He identified gait style-vectors, which represent factors invariant to gait pose. Using a boosted gait content vector, he got a better human identification accuracy than when using the original phase vector before identifying gait content vector.

Hong, Lee, Oh, Park, and Kim [4] have proposed a new feature vector, sampled point vector, for gait recognition based on model-free method. The mean and variance of value of pixels are chosen which are sampled along to central axis of silhouette image for several frames.

Yanmei Chai Jinchang Ren, Rongchun Zhao and Jingping Jia [5] proposed a statistical approach for dynamic gait signature extraction. The DVS on each of the pixel position for a full gait sequence is extracted firstly, and then compute their variance features respectively to construct a dynamic variance matrix as gait signature for identification.

Alam and Hama [6] presented an approach to typify

Pratibha Mishra et al. / (IJAEST) INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING SCIENCES AND TECHNOLOGIES Vol No. 3, Issue No. 1, 020 - 023

ISSN: 2230-7818 @ 2011 http://www.ijaest.iserp.org. All rights Reserved. Page 23

IJAEST

shwetaezra@gmail.com

IJAEST

shwetaezra@gmail.com

walk

IJAEST

walk and recognition is achieved by matching the curves by calculating

IJAEST

and recognition is achieved by matching the curves by calculating the

IJAEST

the side-

IJAEST

side-angle

IJAEST

angle pr

IJAEST

provide

IJAEST

ovide the richest information of the gait of the waking person.

IJAEST

the richest information of the gait of the waking person.

Gaussian

IJAEST

Gaussian membership

IJAEST

membership function ; Control points; Database; Mean; Variance.

IJAEST

function ; Control points; Database; Mean; Variance.

1. INTRODUCTION

IJAEST

1. INTRODUCTION

Gait recognition is a kind of

IJAEST

Gait recognition is a kind of biometrics using the

IJAEST

biometrics using the Gait recognition is a kind of biometrics using the Gait recognition is a kind of

IJAEST

Gait recognition is a kind of biometrics using the Gait recognition is a kind of manner of

IJAEST

manner of individual.

IJAEST

individual. More

IJAEST

More formal

IJAEST

formal definition

IJAEST

definition of

IJAEST

of biometrics is given by [1], “Gait recognition refers to automatic

IJAEST

biometrics is given by [1], “Gait recognition refers to automatic i

IJAEST

individual

IJAEST

ndividual based

IJAEST

based on

IJAEST

on the

IJAEST

the style

IJAEST

style of

IJAEST

of walking”.Gait is treated as a sequence of holistic binary patterns

IJAEST

walking”.Gait is treated as a sequence of holistic binary patterns Approaches

IJAEST

Approaches can

IJAEST

can be

IJAEST

be broadly

IJAEST

broadly categorized

IJAEST

categorized del-based IJA

ESTdel-based ap IJA

ESTapproach, IJA

ESTproach, where IJA

ESTwhere human IJA

ESThuman body IJA

ESTbody structure IJA

ESTstructure

modeled, IJAEST

modeled, an IJAEST

and IJAEST

d the IJAEST

the model-free IJAEST

model-free approach, IJAEST

approach, (silhouettes). IJA

EST(silhouettes). Many IJA

ESTMany st IJA

ESTstudies IJA

ESTudies studies st IJA

ESTstudies st have IJA

ESThave now IJA

ESTnow shown IJA

ESTshown that IJA

ESTthat

to recognize people by the way they walk. It is well-known that IJAEST

to recognize people by the way they walk. It is well-known that powerful IJA

EST

powerful tool IJAEST

tool for IJAEST

for reliable IJAEST

reliable but IJA

EST

but at IJAEST

at present, IJAEST

present, none IJAEST

none biometrics like fingerprints recognitionIJA

EST

biometrics like fingerprints recognition

work IJAEST

work

istant

IJAESTistant camera,

IJAESTcamera, without

IJAESTwithout drawing

IJAESTdrawing the

IJAESTthe

the observed subject.

IJAESTthe observed subject.

performance

IJAESTperformance of

IJAESTof im

IJAESTimage-based

IJAESTage-based image-based im

IJAESTimage-based im gait recognition

IJAESTgait recognition

good because Features extracted from

IJAESTgood because Features extracted from image sequences have a

IJAEST image sequences have a good because Features extracted from image sequences have a good because Features extracted from

IJAESTgood because Features extracted from image sequences have a good because Features extracted from

little

IJAESTlittle difference

IJAESTdifference with

IJAESTwith th

IJAESTthe

IJAESTe original

IJAESToriginal information

IJAESTinformation

ga

IJAESTgait.

IJAESTit. gait. ga

IJAESTgait. ga There is no efficient algorithm proposed yet to

IJAESTThere is no efficient algorithm proposed yet to

the

IJAESTthe difference

IJAESTdifference between

IJAESTbetween th

IJAESTthe

IJAESTe three

IJAESTthree dimensional

IJAESTdimensional

fe

IJAEST

features extracted from projected images

IJAESTatures extracted from projected images

2. RELATED WORKS

IJAEST

2. RELATED WORKS

IJAEST

Chan-Su

IJAEST

Chan-Su Lee

IJAEST

Lee [7]

IJAEST

[7] pre

IJAEST

prepe

IJAEST

people

IJAEST

ople us

IJAEST

using

IJAEST

ing silhouette

IJAEST

silhouette separate

IJAEST

separate two

IJAEST

two independent

IJAEST

independent normalized

IJAEST

normalized gait poses

IJAEST

gait poses ga

IJAEST

gait image

IJAEST

it image gait image ga

IJAEST

gait image gaand

IJAEST

and learning

IJAEST

learning normalized gait phase is used to collect aligned gait poses from

IJAEST

normalized gait phase is used to collect aligned gait poses from di

IJAEST

diffe

IJAESTffe

object contours in a database by a reduced number of data points and to match object shapes in occluded conditions. For simplicity, contours are approximated by a set of membership function. and all control points are stored in the database. Distance matrix is introduced, which is constructed from curve to curve distance measurement between the test and database contours.

3. PROPOSED ALGORITHM

In this paper, we have proposed a new algorithm for recognizing gait system. This algorithm is based on Gaussian membership function. The proposed gait recognition system consists of three units: -(I) Image Preprocessing.(II) Feature Extraction.(III) Gait Recognition.

3.1 Image Preprocessing

In our experiments, there are two assumptions for the human walking sequences: (1) the camera is static and the body in the field of view is not occluded.(2) the image sequence of side-view is used.

Fig 1. Proposed Algorithm

Background subtraction

A simple background extraction method is to subtract a background model from the current frame. This method is based on pixel level processing. The extracted foreground is used for recognition and tracking. This is a very simple and convenient method in motion detection. The difficulty of this method is not the subtraction computation, but maintaining the background model.

There are several classic background subtraction methods. The following methods have self-adaptive ability.1). Mean & threshold method: first compute the mean of background pixels. It is a new biometrics recognition technology. Gait recognition aimed essentially to recognize person by automatically extracting movement characteristic of walking person in the video. Foreground pixels are those that differ by more than a threshold. 2). Mean & variance method update the mean and variance continuously, and then compute the distance. If the distance is larger than the threshold, set the pixels to be the foreground. The gait of a person is best brought out in the side-view [5]. Video of a walking individual is captured by camera and sequence frames are extracted from that video. Each frame is converted into grayscale if it is a color image.

Grayscale images are used in this work because these images are entirely sufficient for our tasks and so there is no need to use more complicated and harder-to-process color images.

Fig. 2 Producing a silhouette from an image.(a) Original Image (b) Silhouette.

Gait Feature Selection

The definition of Gait is defined as “A particular way or manner of moving on foot “Using gait as a biometric is a relatively new area of study, within the realms of computer vision. It has been receiving growing interest within the

Pratibha Mishra et al. / (IJAEST) INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING SCIENCES AND TECHNOLOGIES Vol No. 3, Issue No. 1, 020 - 023

ISSN: 2230-7818 @ 2011 http://www.ijaest.iserp.org. All rights Reserved. Page 24

IJAEST

background

IJAEST

background The following methods have self-adaptive ability.

IJAEST

The following methods have self-adaptive ability.method:

IJAEST

method: first

IJAEST

first compute

IJAEST

compute It

IJAEST

It is

IJAEST

is a n

IJAEST

a new

IJAEST

ew biometrics

IJAEST

biometrics recognition

IJAESTrecognition ai

IJAESTaimed

IJAESTmed aimed ai

IJAESTaimed ai essentially

IJAESTessentially

rson by automatically extracting movement characteristic of

IJAESTrson by automatically extracting movement characteristic of

person

IJAESTperson in

IJAESTin the video.

IJAESTthe video. Fo

IJAESTForeground pixels

IJAESTreground pixels are

IJAESTare

r by more than a threshold.

IJAESTr by more than a threshold.

ean

IJAESTean &

IJAEST& variance

IJAESTvariance method

IJAESTmethod update

IJAESTupdate the

IJAESTthe mean

IJAESTmean

continuously, and then compute the distance. If the distance is

IJAESTcontinuously, and then compute the distance. If the distance is

larger

IJAESTlarger than

IJAESTthan the

IJAESTthe threshold,

IJAESTthreshold, set

IJAESTset the

IJAESTthe pixels

IJAESTpixels to

IJAESTto

The

IJAESTThe ga

IJAESTgait

IJAESTit gait ga

IJAESTgait ga of

IJAESTof a

IJAESTa person

IJAESTperson is

IJAESTis best

IJAESTbest brought

IJAESTbrought out

IJAESTout

Video

IJAESTVideo of

IJAESTof a

IJAESTa walking

IJAESTwalking individual

IJAESTindividual is

IJAESTis

sequence

IJAEST

sequence frames

IJAEST

frames are

IJAEST

are extracted

IJAEST

extracted from

IJAEST

from converted into grayscale if it is a color image.

IJAEST

converted into grayscale if it is a color image.

IJAEST

Grayscale

IJAEST

Grayscale images

IJAEST

images are

IJAEST

are images

IJAEST

images are

IJAEST

are entirely

IJAEST

entirely sufficient

IJAEST

sufficient ne

IJAEST

need

IJAEST

ed to

IJAEST

to use

IJAEST

use more

IJAEST

more images.

IJAEST

images.

IJAEST

IJAEST

computer vision community and a number of gait metrics have been developed. An important issue in gait is the extraction of appropriate salient features that will effectively capture the gait characteristics. The features must be reasonably robust to operating conditions and should yield good discriminability across individuals. A fast and efficient method is adopted to select only most discriminative features.

Fig 3. a) Sequence of selecting control points.

Fig 3. b) Skeleton model of human frame

3.2.1 Key Frames Generation

We determine the key frames of a walking gait by observing the different phases of a human walk cycle as shown in Figure. The first key is defined at the pose where front leg is standing straight while the back leg is bend and slight above the ground. The second key is at the location where the front leg’s foot is flat on the ground and back leg’s toe touches the ground. The third key is defined as the pose where the back leg’s foot if flat on the ground and front leg’s ankle touches the ground. The fourth key will return back to the first key and complete the cycle.

Fig 4. Key Frames

3.2.2 Computation of Gaussian membership function

The Gaussian Membership function was chosen because of its popularity and simplicity.

The formula is given below [2]:-

μ A(x) = -exp (x – m)2/2σ2

Where X represents the crisp data,μ represents the membership function of x,m represents the mean of all the crisp data x in the distribution andσ represents the variance of all the crisp data in the distribution.

The variance σ can be represented mathematically as

σ = √ (Σ(x – m) 2/n)

Where n is the number of angles in the distribution,x represents the crisp data andm represents the mean of all the crisp data x in the distribution.

The Gaussian membership function was used to fuzzify all the crisp data obtained. The data for each subject was stored in the knowledge base and used for the inference when a gait pattern or signature is to be tested, classified and recognized. The actual Gaussian membership function obtained for the crisp data for all the four patterns associated with the five subjects.

Once the control points are given, the curve shape is determined.

3.3 Gait Recognition

The experiment involves capturing subtle changes in an individual’s walk, taking into consideration the variation in angles of the various parts of the body or the amplitude of the

1. ankle2. Toe3. Knee4. Palm5. Shoulder

Pratibha Mishra et al. / (IJAEST) INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING SCIENCES AND TECHNOLOGIES Vol No. 3, Issue No. 1, 020 - 023

ISSN: 2230-7818 @ 2011 http://www.ijaest.iserp.org. All rights Reserved. Page 25

IJAEST

b) Skeleton model of human frame

IJAEST

b) Skeleton model of human frame

3.2.1 Key Frames GenerationIJAEST

3.2.1 Key Frames Generation

determine the IJAEST

determine the key IJAEST

key frames IJAEST

frames of IJAEST

of a IJAEST

a walking IJAEST

walking gait IJAEST

gait the different phases IJA

ESTthe different phases of a human IJA

ESTof a human walk cycle as IJA

ESTwalk cycle as

defined IJAEST

defined at IJAEST

at thIJAEST

the IJAEST

e pose IJAEST

pose where IJAEST

where raight while the back leg is bend IJA

EST

raight while the back leg is bend and slight above the ground. IJAEST

and slight above the ground. t IJA

EST

the IJAEST

he the t IJAEST

the t location IJAEST

location where IJAEST

where back IJA

EST

back leg’s IJAEST

leg’s defined as the pose where the back leg’s foot if flat IJA

EST

defined as the pose where the back leg’s foot if flat

Computation of Gaussian membership function

IJAEST

Computation of Gaussian membership function

The Gaussian Membership function was chosen because of its

IJAESTThe Gaussian Membership function was chosen because of its

popularity and simplicity.

IJAESTpopularity and simplicity.

The formula is given below

IJAESTThe formula is given below [2]

IJAEST [2]The formula is given below [2]The formula is given below

IJAESTThe formula is given below [2]The formula is given below :-

IJAEST:-μ A(x) = -exp (x – m)

IJAESTμ A(x) = -exp (x – m)2

IJAEST2/2σ

IJAEST/2σ2

IJAEST2

Whe

IJAESTWhere

IJAESTre

X

IJAESTX re

IJAESTrepr

IJAESTprreprre

IJAESTreprre esents the crisp data,

IJAESTesents the crisp data,

μ

IJAESTμ represents the mem

IJAESTrepresents the membership function of x,

IJAESTbership function of x,represents the membership function of x,represents the mem

IJAESTrepresents the membership function of x,represents the mem

m

IJAEST

m represents the mean of all the crisp data x in the distribution

IJAEST

represents the mean of all the crisp data x in the distribution and

IJAEST

andσ

IJAEST

σ represents

IJAEST

represents the

IJAEST

the variance

IJAEST

variance di

IJAEST

distribution.

IJAESTstribution.

The variance σ can be represented mathematically as

IJAEST

The variance σ can be represented mathematically as

σ = √ (Σ(x – m)

IJAEST

σ = √ (Σ(x – m)

Whe

IJAEST

Where n is the number of angles in the distribution,

IJAEST

re n is the number of angles in the distribution,x

IJAEST

x represents the crisp data and

IJAEST represents the crisp data and

m

IJAEST

m

IJAEST

persons walking pattern. There are three different stages:Stage 1: Video SequenceStage 2: Points selection.Stage 3: Points Processing

Video Sequence

Each subject had a total of five markers (objects capable of reflecting light over a camera) attached to the following parts of their body:1. The Shoulder2. The Hip3. The Knee4. The Ankle5. The Toe

The video of each subject’s gait pattern was captured randomly using the installed camera. For each captured gait pattern, a mark-in point and mark-out point was chosen arbitrarily. The mark-in point represents the first point in the captured gait video where all the markers were visible, while the mark out point represents the last point in the video where the five markers were visible. These mark-in points and mark-out points were arbitrary in the sense that different points were chosen for each subjects captured gait video.

Points selection

After the mark-in and mark-out points were chosen for each captured gait video, the data points were cropped between the start and finish markers. Whenever the markers exceeded the software’s default minimum and maximum outline, the setup was changed 6 to accommodate the excesses. The cropped data points were digitized automatically by the software using the centriod of each marker. For points like those of the hips which could not be digitized automatically by the software, as a result of the obstruction caused by the arm during the gait, the cursor location was used to digitize the points instead.

Points Processing

The digitized points were processed by the process wizard in the software. The 2-dimensional angles of rotation of the marked parts of the body were saved in system as database. Reflex angles were recorded for the hip, torso and ankle movement, while obtuse angles were recorded for the knee movement as shown in the stick diagram below. We adopted a

simple and straightforward way in order to test the recognition capability of our proposed method. First we calculate the variance of x- and y- coordinates of any curve of all frames of an individual separately and then finally calculate the mean of x- coordinate with its corresponding y- coordinate. In contrast to other system, proposed features are very simple and require low storages.

Advantages of Proposed Method:

1. The Gaussian Membership function is chosen because of its popularity and simplicity.2. It does not require silhouette images and GEI images.3. Computational speed becomes high due to use of simple mathematical calculations like mean and variance.

CONCLUSION

The membership functions associated with each resemblance is also displayed we proposed a novel gait recognition method based on the Gaussian membership function. First we select the points on sequence frames, calculate the coordinates of Gaussian membership function from those points, draw the curves and finally, calculate thevariance and mean from Gaussian membership function coordinates. These variance and mean are used to fulfill the person identification.

REFERENCES

[1] Xiaxi Huang and Nikolaos V. Boulgouris, “Gait Recognition Using Multiple Views”, IEEE 2008.[2] Elizabeth I. Maduko, “pattern recognition of human gait signatures”.[3] Seungdo Jeong, Su-Sun Kim, Byung-Uk Choi, “Canonical View Synthesis for Gait Recognition”, IEEE 2007.[4] Sungjun Hong, Heesung Lee, Kyongsae Oh, Mignon Park, and Euntail Kim, “Gait Recognition using Sampled Point Vectors”, IEEE 2006.[5] Yanmei Chai Jinchang Ren, Rongchun Zhao and Jingping Jia, “Automatic Gait Recognition using Dynamic Variance Features”, IEEE 2006.[6] Md. Jahangir Alam and Hiromitsu Hama, “Occluded Shape Matching for Image Database of Reduced Data Points”, IEEE.[7] Chan-Su Lee, “Identification of people using silhouette gait image”.

Pratibha Mishra et al. / (IJAEST) INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING SCIENCES AND TECHNOLOGIES Vol No. 3, Issue No. 1, 020 - 023

ISSN: 2230-7818 @ 2011 http://www.ijaest.iserp.org. All rights Reserved. Page 26

IJAEST

After the mark-in and mark-out points were chosen for each

IJAEST

After the mark-in and mark-out points were chosen for each cropped

IJAEST

cropped between

IJAEST

between the

IJAEST

the markers

IJAEST

markers exceeded

IJAEST

exceeded the

IJAEST

the maximum

IJAEST

maximum outline,

IJAEST

outline, the

IJAEST

the setup

IJAEST

setup ccommodate the excesses. The cropped data

IJAEST

ccommodate the excesses. The cropped data by

IJAEST

by the

IJAEST

the software

IJAEST

software using

IJAEST

using the

IJAEST

the centriod of each marker. For points like those of the hips which

IJAEST

centriod of each marker. For points like those of the hips which automatically

IJAEST

automatically by the software,

IJAEST

by the software, as a

IJAEST

as a result

IJAEST

result by the

IJAEST

by the arm

IJAEST

arm during

IJAEST

during the gait, the

IJAEST

the gait, the cursor

IJAEST

cursor location was used to digitize the points instead.

IJAEST

location was used to digitize the points instead.

The digitized points were processed by the process wizard in IJAEST

The digitized points were processed by the process wizard in software. IJA

ESTsoftware. The IJA

ESTThe 2-dimensional IJA

EST2-dimensional angles IJA

ESTangles of IJA

ESTof rotation IJA

ESTrotation

parts IJAEST

parts of IJAEST

of the body IJAEST

the body were IJAEST

were saIJAEST

saved IJAEST

ved saved saIJAEST

saved sa in IJAEST

in system IJAEST

system angles IJA

ESTangles were IJA

ESTwere recorded IJA

ESTrecorded for IJA

ESTfor the IJA

ESTthe hip, IJA

ESThip,

while IJAEST

while obtuse IJAEST

obtuse angles IJAEST

angles were IJAEST

were recorded IJAEST

recorded shown IJA

EST

shown in IJAEST

in the IJAEST

the stick IJAEST

stick diagram IJAEST

diagram

The Gaussian Membership function

IJAEST The Gaussian Membership function

. It does not require silhouette images and GEI images.

IJAEST. It does not require silhouette images and GEI images.. Computational speed becomes high due to use of simple

IJAEST. Computational speed becomes high due to use of simple

mathematical calculations like m

IJAESTmathematical calculations like mean and variance.

IJAESTean and variance.mathematical calculations like mean and variance.mathematical calculations like m

IJAESTmathematical calculations like mean and variance.mathematical calculations like m

CONCLUSION

IJAEST CONCLUSION

The

IJAESTThe membership

IJAESTmembership functions

IJAESTfunctions associated

IJAESTassociated

mblance

IJAESTmblance is

IJAESTis a

IJAEST also

IJAESTlso displayed

IJAESTdisplayed we

IJAESTwe proposed

IJAESTproposed cognition

IJAESTcognition method

IJAESTmethod based

IJAESTbased on

IJAESTon the

IJAESTthe Gaussian

IJAESTGaussian

function.

IJAESTfunction. First

IJAESTFirst we

IJAESTwe select

IJAESTselect the

IJAESTthe points

IJAESTpoints

calculate

IJAESTcalculate the

IJAESTthe co

IJAESTcoordinates

IJAESTordinates of

IJAESTof Gaussian

IJAESTGaussian

from

IJAEST

from those

IJAEST

those points,

IJAEST

points, draw

IJAEST

draw the

IJAEST

the c

IJAEST

curves

IJAEST

urves va

IJAEST

variance

IJAEST

riance variance va

IJAEST

variance va and

IJAEST

and mean

IJAEST

mean from

IJAEST

from Gaussian

IJAEST

Gaussian coordinates.

IJAEST

coordinates. These

IJAEST

These variance

IJAEST

variance pe

IJAEST

person identification

IJAEST

rson identification.

IJAEST

.

[1]

IJAEST

[1] Xiaxi

IJAEST

Xiaxi Huang

IJAEST

HuangUsing Multiple Views”, IEEE 2008.

IJAEST

Using Multiple Views”, IEEE 2008.[2]

IJAEST

[2] Elizabeth

IJAEST

Elizabeth signatures”.

IJAEST

signatures”.[3]

IJAEST

[3] Seungdo Jeong, Su-Sun Kim, Byung-Uk Choi, “Canonical View

IJAEST

Seungdo Jeong, Su-Sun Kim, Byung-Uk Choi, “Canonical View Synthesis for Gait Recognition”, IEEE 2007.

IJAEST

Synthesis for Gait Recognition”, IEEE 2007.