The is to quantitatively evaluate the proposed

The machines and robots interact with the
human with the help of embedded system. for example, with the help of hand
gesture machine and human interaction. This interaction can be possible with
the implementation of the embedded
system. With the advancement in technology,
the machine vision is used to identify the various human gestures, in some
system wheeled robots can be used to
identify the human gesture. Some embedded system would not support the usage of
Kinect due to its volume and weights. The computation time related to this
embedded platform is high. Therefore, it is necessary to reduce the computation
time of these embedded systems. This can be reduced by categorizing the skin
areas and non- skin areas of the hand.  The significance of this study is to
quantitatively evaluate the proposed hypothesis to fill the identified research
gaps related to proposed methodology. The gesture
is defined as the way that can be used to
understand the significant changes related to hand moments that can be possible
with the help of embedded systems. The embedded systems. Embedded system is computers that can be used for real time
computing. the embedded systems are integrated with other system and that
include mechanical and hardware parts. As compared to general computers the
embedded system consumes less power, consumes less cost, small in size and
rugged operating system that can be used to perform real time computations. The
human gestures can be recognized with the help of machine learning algorithms
and classification of the images can be done according to the various features
of the image. The classification of the image can be done according to the skin area of
and non-skin area of the hand. The are
several types of embedded system that can be useful in our daily life but in
our approach, we have used these systems
for identifying the human gestures.   

Statement of problem and sub problems

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

This research is conducted to reduce the
time of the various computational statistics that are involved while
recognizing the hand gesture. Some embedded system does not support the usage
of Kinect due to its volume and weights. The computation time related to this
embedded platform is high. Therefore, it is necessary to reduce the computation
time of these embedded systems. This can be reduced by categorizing the skin
areas and non- skin areas of the hand.
The real time recognition can be done by using Gaussian mixture model. this
types of intelligent robots can be used for security and privacy purpose.
Following are the sub-problems of the proposed
algorithm:

Sub-problem1:
The accuracy rate of the proposed
algorithm to analyze the input image: The problem related to accuracy and
detection rate of images has been analyzed with the help of quantitative
analysis. The detection of images can be done in a reduced number of computation related to conventional approaches.      

Limitations of study

Following
are the limitations of conducted research:

·        
The result evaluation and
analysis of proposed methodology is out of the scope
of this study.

·        
Large scale dataset is
not included in this study. Gaussian mixture model algorithm is evaluated with
the help of a limited number of images.

·        
The average rate of
recognition related to adopted algorithm or approach is 75%. It can be improved.
The images recognized with the help of proposed recognition are less. It can be
improved by using a number of machine
learning algorithms.

·        
The data input to the
proposed approach is not variant. Variant data can be used to evaluate the
originality of algorithm. the number of resources from the data is collected is
limited. More will be the data more will be originality of conducted research.

Hypothesis

The hypothesis related to the reduction of computational time can be
evaluated with the help of proposed analysis. it is assumed that system would
be capable of detecting the various hand gesture in an effective manager as
compared to conventional approaches. following is the hypothesis of proposed
approach:

H1: The computational time can be reduced
with the implementation of proposed algorithm

H2:  The computational time cannot be reduced with
the implementation of proposed algorithm

H3: The proposed system can detect the
hand gesture with the help of Gaussian mixture model