Abstract :
|
Computer is used by many people either at their work or
any other time. Special input and output devices have been
designed over the years with the purpose of easing the
communication between computers and humans. This leads
to the new types of human-computer interaction (HCI).
Speech, facial expressions and human gestures are some
steps towards to make the computer can understand. There
is non-verbally exchanged information that is gestures.
Innumerable gestures can be performed by the person at a
time. Gestures are expressive, meaningful body motions.
Interpretation of human gestures such as hand movements
or facial expressions, using mathematical algorithms is
done using gesture recognition. In this research a technique
to recognize the hand gesture by using the neural network
has been done. The feed backward neural network is used
on the basis of train images to get the distance ratio. Then
the SIFT (scale invariant feature extraction) is used to
extract the feature points of test image. The images having
the greater ratio as compared to threshold distance ratio are
rejected. The database image having largest key-points
matched with test image is the resultant image. In this work
we have tested the proposed algorithm 30 sign images of
ASL. The simulation result show that the true match rate is
increased from 77.7% to 84% while the false match rate is
decreased from 8.33 % to 7.4%, as compared to the
previous research data.
|