CSEIT183179 | Received : 10 Jan 2018 | Accepted : 25 Jan 2018 | January-February-2018 [(3) 1 : 487-491 ]
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
© 2018 IJSRCSEIT | Volume 3 | Issue 1 | ISSN : 2456-3307
487
Image Based Sign Language Recognition using Neuro - Fuzzy Approach
Hemina Bhavsar
*1
, Dr. Jeegar Trivedi
2
*1
Department of Computer Science, S. S.Agrawal Institute of Computer Science, Navsari , Gujarat, India
2
Department of Computer Science, Sardar Patel University Anand, Gujarat, India
ABSTRACT
Sign language is the language of deaf & dumb people. They expressed their thoughts in the form of sign
language. This paper proposed sign language recognition (SLR) system which is the computerized system useful
for translation of sign language into English language in the form of text. It will be use video data of deaf &
dumb people and translate into English text. Proposed system recognizes both hand movements including face.
Various image processing techniques are defined in this paper which will use for process the images. Convex
hull feature extraction method will be applied for extract features which will classify by Neuro-Fuzzy
classification approach. Recognized words will be inputted into NLP (Natural Language Processing) engine to
format into the sentence.
Keywords: NLP, SLR
I. INTRODUCTION
Language that is used by deaf and dumb people is
called Sign Language. Deaf and dumb people, who
cannot speak or listen but only can see, are using this
language to express their thought. They are talk with
each other by sign Language. Normal People cannot
identify that exactly what Deaf people wants to say.
So here we need either a translator who can translate
signs into normal language or normal people have to
learn this sign language.
At each time we cannot get translator/Interpreter
easily. Because availability of translator is limited and
expensive also. So the solution of this problem is that
we have to use some automatic system that can
automatically translate signs into spoken language.
Sign Language Recognition system is the automatic
computerized system that automatically recognize
signs and translate into normal language. This system
is technically sound but also very important in
Human Society. Deaf and dumb people can easily
communication with normal people, express their
ideas, thoughts etc. SLR system can be used in verity
of ways in daily life, like this system can be used in
Bank, Post Office, and Shopping Mall etc. In this
type of places deaf people can easily communicate
with other people and fulfill their requirements. In
Education also this system very useful where deaf
people can also become a teacher. This can improve
confidence of Deaf and Dumb people to live in
society.
II. RELATED STUDY
M. V. D. Prasad, P. V. V. Kishore, E. Kiran Kumar, D.
Anil Kumar [1], presented methods for Indian Sign
Language Recognition. Wavelet based fusion of two
weak edge detection models. One is morphological
subtraction model and the other is gradient based
canny edge operator. Elliptical Fourier descriptors
provide shape models used with optimized number
of shape descriptors. Principle components
determined find the feature vector to a minimum to
accommodate all the frames in the video sequence.
Classification of the signs is done by Back
Propagation Neural Network Algorithm. The
recognition rate stands at 92.34%.