Beruflich Dokumente
Kultur Dokumente
Abstract
The problems tackled by hearing and speech impaired people
while interacting with normal people can be easily overcome
by construction of a communication system which allows
communicate impaired people to communicate other without a
middle interpreter. The proposed system is a cost-effective and
possible to minimize the distance between hearing and speech
impaired people with normal people. Proposed system
captures the hand signs and compare with existing database
and then accordingly converted into text followed by speech in
a commonly spoken language like English. This system is
using an Image Processing algorithm which processes the
detection and extraction of the input hand gesture from the
image stream. In this system we are using functions like skin
color based thresholding, contour detection and convexity
defect (convex hull) for detection of hands and identification
of important points on the hand respectively. The distance
between these contour points from the centroid of the hand
becomes our feature vector against which we will train our
neural network.
Keywords Image Processing, Hand Gesture Recognition,
Convex-Hull, Neural Networks.
Introduction
Related work
The use of hand gestures is an important area in the
development of intelligent human interaction systems. In the
A lot of researches work has been done in the arena of
field of Gesture recognition we have large number of innocomputerization
of sign language interpreter to make schemes
vations. The gestures can be defined as a physical action,
that
successfully
interpret hand gestures into speech and text.
which can convey the information. Sign language is mainly
The two main methods for identifying hand gesture for the
imitated by using hand gestures as communication medium
hearing and speech impaired people while interacting with
among people having vocal and hearing impairments so that
normal people are glove based techniques and vision based
they can communicate to normal peoples. A person who can
techniques [1],[2]. A novel approach presented by
talk and hear properly cannot communicate with a mute perRaghavendra[3] to detect hand gestures which are a part of
son unless he is aware with sign language. A lot of work has
sign language, by utilizing special color coded gloves. The
been carried out in the field of automation of sign language
capturing image from the camera, the very first step is
interpretation to make use of systems effectively to translate
segmentation that is isolating the hand region from the
signs i.e. hand gestures into speech or text. Hand gesture is an
captured image [12]. The methods for object segmentation
ideal option for expressing the feelings or in order to convey
mainly depends on the color model that can be extracted from
something like representing a number, words.
the existence RGB color model which could be HSV color
We can use hand as an input and by making its gesture
model or YCbCr color space [13], The thresholding is done on
understandable to computer database we can interpret the text.
the basis of Otsus method [14]. A vision-based scheme able
In this paper we are presenting a method to recognizing the
to identify 14 gestures in real time to handle windows was
various hand gestures, converting them into the text and then
developed by C.W. Ng in [4]. F.Ullah has intended a system
into voice.
ISSN No: 2250-3536
E-ICETT 2014
81
12.92
0.055+
C=
1.055
0.03928
2.4
Y1=
System Architecture
Figure 1 shows the key components of our system that
transform the sign language symbols and compare in database
to convert into corresponding text followed by speech.
Z1=
n
Where:
X1 = X11/3
ifX1>0.008856
= 7.787X1+16/116
else
Y1 = Y11/3
ifY1>0.008856
= 7.787Y1+16/116
else
Z1 = Z11/3
ifZ1>0.008856
= 7.787Z1+16/116
else
Then,
L*=116 Y1-16
a*=500(X1-Y1)
b*=200(Y1-Z1)
Matrix
u xr/yw vxg/yw wxb/yw
Cxr =
u yr/yw vyg/yw wyb/yw
u zr/yw vzg/yw wzb/yw
Bradford matrix
B= M-1cx D Mcx
L*a*b is CIE specification that attempts to make the
luminance scale more perceptually uniform L* is a nonlinear
scaling of L normalized to a reference white point. Otsu's
method is used to automatically perform clustering-based
image thresholding, [14] or the reduction of a gray level image
to a binary image.
Let the g(x, y) is binary image is defined as:
g(x,y)=
1
0
(, )
(, ) <
pr (rq) =
q=1,1,2,..L-1
E-ICETT 2014
82
B. Feature extraction
Features extraction plays an important role in the whole
process. It is only the features which decide the accuracy of
the algorithm. Initially many other techniques were used for
the feature extraction, which includes color, texture etc. but
these feature may vary from person to person as each person
can have different tone of color, and it may also be affected by
varying lightning conditions. Once the hand is identified and
separated from the rest of the image then it is processed
further to determine the centroid and convex hull of the given
shape.
In proposed scheme we are working on vision based hand
gesture recognition techniques, which mainly focus on the
shape of the hand. The moments are structures of the hand
which allow rebuilding of the object, the central and spatial
moments are determined and the centroid of the hand is
calculated as follows:
Mi,j= f yf I(x,y)
Where I (x, y) defines the intensity at coordinate of the
centroid (x, y) is found by using;
x
M10
M00
0
255
M01
M00
<
<
, ,2
Let
Dn= { f(d1),f(d2),f(d3),,f(dn)}
Be the normalized defect location
E-ICETT 2014
83
Results
This hand motion translator is clever to translate Indian
sign (A-Z) and numbers (0-9). All the motion can be translated
real-time. The current system has only been trained to skin
color thresholding and convex hull are applied on images and
get result.
The proposed algorithm is applied on small database of
images with Different hand movements. With the help of
defined features extraction skin color thresholding and convex
hull, we can successfully recognize the different hand
movement patterns sample result is shown in below diagram.
Conclusion
A simple sign language interpretation system is developed
which uses a user-specific training for an independent signer,
dialect free sign language translation without the system
relying on expensive additional hardware such as data gloves
or sensors. We have proposed a simple and novel feature set
that can be extracted in real time. The non-intrusive solution
we are aiming to achieve reasonable average accuracies and
maximum recognition accuracy on numerals and alphabets
respectively.
Future work will revolve exploration use simple neural
network with back-propagation learning algorithm for training
and testing and generalization abilities across different sign
languages and improving upon the accuracy rates.
Acknowledgments
Future work
References
E-ICETT 2014
84
Biographies
PANKAJ PATIL received the B.E. degree in Electronics
Engineering from the Shivaji University, Kolhapur,
Maharashtra, in 2012. Currently, He is pursuing the M.E.
degree in Electronics and Telecommunications Engineering in
VLSI and Embedded engineering. Author may be reached at
pankspatil5310@gmail.com
G. V. LOHAR currently working as a Professor in S.I.T.,
Lonavala in Electronics and Telecommunication department.
Author may be reached at Ganeshlohar73@gmail.com
E-ICETT 2014
85