Authors :
Vikas; Rahul Mandal
Volume/Issue :
Volume 7 - 2022, Issue 5 - May
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3avweBd
Abstract :
The utilization of physical controllers like
mouse, keyboards for HCI impedes the regular point of
interaction as there is a solid boundary between the user
and the PC. Hence, different strategies are assembled
like speech, joint movement, and hand sign procedures
to make it more natural and appealing. Over the most
recent couple of years, hand gesture recognition has been
viewed as an easy and normal procedure for humanmachine communication. It is one of the methods for
correspondence with PCs utilizing static and dynamic
development and helps us perceive messages utilizing
them. Numerous applications have been developed and
upgraded for hand sign recognition. These applications
range from cell phones to cutting-edge advanced robotics
and from gaming to clinical science. In the vast
commercial and research applications, recognition of
hand signs has been performed by utilizing sensor-based
wired installed gloves or by utilizing vision-based
methods where skin tones, chemicals, or paperclips are
utilized on the hand. In any case, it is attractive to have
hand sign recognition techniques that are pertinent to a
natural and bare hand. Today data of various
researchers and now available to experiment with Hand
Sign Recognition. We have used TensorFlow, OpenCV,
and Jupyter Notebook for developing the Sign
Recognition System where we have trained our model
for various sign languages and alphabets. We have used
Object Detection Technique to build this system where
our webcam takes the input data and trains the system
which is working in a virtual environment. Data
accuracy depends on speed. So higher the speed lowers
the accuracy and vice-versa. Using different hand signs
to advance continuous application we pick a Visionbased Hand Gesture Recognition System that depends
on various shape features.
Keywords :
Human-Computer Interaction, Data Gloves, Optical Markers, Image-Based Technologies, Vision-Based Recognition System, OpenCV, Jupyter Notebook, Tensorflow
The utilization of physical controllers like
mouse, keyboards for HCI impedes the regular point of
interaction as there is a solid boundary between the user
and the PC. Hence, different strategies are assembled
like speech, joint movement, and hand sign procedures
to make it more natural and appealing. Over the most
recent couple of years, hand gesture recognition has been
viewed as an easy and normal procedure for humanmachine communication. It is one of the methods for
correspondence with PCs utilizing static and dynamic
development and helps us perceive messages utilizing
them. Numerous applications have been developed and
upgraded for hand sign recognition. These applications
range from cell phones to cutting-edge advanced robotics
and from gaming to clinical science. In the vast
commercial and research applications, recognition of
hand signs has been performed by utilizing sensor-based
wired installed gloves or by utilizing vision-based
methods where skin tones, chemicals, or paperclips are
utilized on the hand. In any case, it is attractive to have
hand sign recognition techniques that are pertinent to a
natural and bare hand. Today data of various
researchers and now available to experiment with Hand
Sign Recognition. We have used TensorFlow, OpenCV,
and Jupyter Notebook for developing the Sign
Recognition System where we have trained our model
for various sign languages and alphabets. We have used
Object Detection Technique to build this system where
our webcam takes the input data and trains the system
which is working in a virtual environment. Data
accuracy depends on speed. So higher the speed lowers
the accuracy and vice-versa. Using different hand signs
to advance continuous application we pick a Visionbased Hand Gesture Recognition System that depends
on various shape features.
Keywords :
Human-Computer Interaction, Data Gloves, Optical Markers, Image-Based Technologies, Vision-Based Recognition System, OpenCV, Jupyter Notebook, Tensorflow
