2 / 18
allied
academies
Page 19
7
th
International Conference on
Recycling and Waste Management
October 03-04, 2019 | Melbourne, Australia
Journal of Environmental Waste Management and Recycling | Volume: 02
Plastic Waste Classification System using image processing and deep learning
Janusz Bobulski
and
Mariusz Kubanek
Czestochowa University of Technology, Poland
T
he plastic waste management is a challenge for the
whole world. Manual sorting of garbage is a tedious
and expensive process, which is why scientists create and
study automated sorting techniques to improve the overall
efficiency of the recycling process. The plastic waste might
be automatically selected on the sorting lines businesses
for waste disposal by using methods of image processing
and artificial intelligence, especially deep learning, to
improve the overall efficiency of the recycling process.
Waste segregation techniques and procedures are applied
to major groups of materials such as paper, glass, metal,
wood, and plastic. However, the biggest challenge is
separating different types of materials in a given group,
e.g. sorting different colors of glass or different types of
plastics. The problem of plastic garbage is interesting
and important at the same time due to the possibility
of recycling only certain types of plastics (e.g. PET can
be converted into polyester material). Thus, there is a
problem with the separation of different types of plastics,
some of which can be reused. One of the possibilities is the
use of deep learning and convolutional neural network. In
household waste, the most are plastic components, and
the four dominant types: PET - polyethylene terephthalate,
HDPE - high-density polyethylene, PP- polypropylene, PS-
polystyrene. The main problem considered in this article
is the creation of an automatic plastic waste segregation
method, which can separate four mentioned categories:
PS, PP, PE-HD and PET, and could be applicable on a sorting
plant.
Speaker Biography
Janusz Bobulski has completed his PhD at the age of 29 years from
Czestochowa University of Technology, Poland; in 2018 he received
habilitation. He is the Associate Professor of Czestochowa University
of Technology, Poland. He has over 70 publications that have been
cited over 70 times, and his/her publication H-index is 5 and has
been serving as an editorial board member of reputed Journals. His
scientific interests include: artificial intelligence, image processing and
recognition, pattern recognition, deep learning.
e:
januszb@icis.pcz.pl