Abstract:
In this project we decided to make a size prediction system that would measure and
predict the size of people based on camera footage, The reason for this is the growing
amount of uneasiness between people due to the covid outbreak, policies and
behavioural changes that came along with that, going to a store and asking someone
to measure your size is very anxiety inducing for most people, not to mention the
workers at the shop which would like to be covid free as well, secondly changing
or try out rooms which were a common place to check clothing before buying
have been deemed unusable due to being occupied by people, and anything that has to
be shared has the highest chance of passing on covid. So, we decided to make a system
that would measure size without needing any human intervention. We had multiple
plans of action to achieve the means but we settled on using purely camera and
computer vision due to the vast of amount of research that has already been done in
detecting human bodies through computer vision, also the python libraries that help
and facilitate machine learning and model creation are a blessing to have, working
any kind of third party non-conventional system would make things harder and not
on
scalable. So, We decided to use computer vision to identify human bodies and measure
them using distance equations, Once done we outputted the data to a excel sheet, from
which we can read the data into a website and recommend clothes from there. In this
endeavour we chose to make a size prediction framework that would gauge and foresee
the size of individuals in light of camera perspective using Computer Vision
