Designing an Assistive Mouse for Human Computer Interaction Using Hand Gestures

Michael Qi

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2021-119
May 14, 2021

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2021/EECS-2021-119.pdf

While computers have become increasingly prevalent in recent years, they are not accessible to all people. Although technology has advanced tremendously, human computer interaction systems have not evolved to the same degree since their conception. In fact, the traditional computer mouse used today was first designed more than 50 years ago. However, as computer users grow increasingly diverse, the limitations of the mouse become more apparent. To provide a greater degree of flexibility for a wide variety of people, we must develop alternative systems of human computer interaction. We propose an assistive mouse for people who are unable to use a traditional mouse comfortably due to physical limitations. It uses hand tracking and gesture recognition to enable cursor movement and mouse actions, respectively. Furthermore, it incorporates anti-shake filters to help people with essential tremors. Through our evaluation, we have confirmed that each of the component modules achieves high accuracy and precision. As a result, the system is currently operable.

Advisor: Brian A. Barsky


BibTeX citation:

@mastersthesis{Qi:EECS-2021-119,
    Author = {Qi, Michael},
    Title = {Designing an Assistive Mouse for Human Computer Interaction Using Hand Gestures},
    School = {EECS Department, University of California, Berkeley},
    Year = {2021},
    Month = {May},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2021/EECS-2021-119.html},
    Number = {UCB/EECS-2021-119},
    Abstract = {While computers have become increasingly prevalent in recent years, they are not accessible to all people. Although technology has advanced tremendously, human computer interaction systems have not evolved to the same degree since their conception. In fact, the traditional computer mouse used today was first designed more than 50 years ago. However, as computer users grow increasingly diverse, the limitations of the mouse become more apparent. To provide a greater degree of flexibility for a wide variety of people, we must develop alternative systems of human computer interaction.
We propose an assistive mouse for people who are unable to use a traditional mouse comfortably due to physical limitations. It uses hand tracking and gesture recognition to enable cursor movement and mouse actions, respectively. Furthermore, it incorporates anti-shake filters to help people with essential tremors. Through our evaluation, we have confirmed that each of the component modules achieves high accuracy and precision. As a result, the system is currently operable.}
}

EndNote citation:

%0 Thesis
%A Qi, Michael
%T Designing an Assistive Mouse for Human Computer Interaction Using Hand Gestures
%I EECS Department, University of California, Berkeley
%D 2021
%8 May 14
%@ UCB/EECS-2021-119
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2021/EECS-2021-119.html
%F Qi:EECS-2021-119