Probabilistic white strip approach to plastic bottle sorting system

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

One of the most important steps in plastic recycling industry is waste sorting. Plastic wastes are usually sort into two main categories, which are polyethylene terephthalate (PET) and non-PET. This paper proposes a probabilistic approach to automated plastic bottle sorting by integrating size, colour and distance modelling of the plastic waste. Firstly, white strips are identified by employing maximum likelihood approach. Information on the white and grey strips is then analyzed by using maximum a posteriori method. Feature histogram is built by factoring the output decision of each white strip with its size. Finally, likelihood test is performed to classify the waste into PET and non-PET. Our algorithm performs the best in all evaluation metrics compared to the benchmark algorithms. It is most suitable to be implemented in a factory with the ever changing surroundings.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Pages3162-3166
Number of pages5
DOIs
Publication statusPublished - 2013
Event2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC
Duration: 15 Sep 201318 Sep 2013

Other

Other2013 20th IEEE International Conference on Image Processing, ICIP 2013
CityMelbourne, VIC
Period15/9/1318/9/13

Fingerprint

Plastic bottles
Sorting
Polyethylene terephthalates
Plastics
Maximum likelihood
Industrial plants
Color
Industry

Keywords

  • Likelihood test
  • Maximum a posteriori
  • Maximum likelihood classification
  • PET bottle identification
  • Plastic recycling

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Zulkifley, M. A., Mustafa, M. M., & Hussain, A. (2013). Probabilistic white strip approach to plastic bottle sorting system. In 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings (pp. 3162-3166). [6738651] https://doi.org/10.1109/ICIP.2013.6738651

Probabilistic white strip approach to plastic bottle sorting system. / Zulkifley, Mohd Asyraf; Mustafa, Mohd. Marzuki; Hussain, Aini.

2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 3162-3166 6738651.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zulkifley, MA, Mustafa, MM & Hussain, A 2013, Probabilistic white strip approach to plastic bottle sorting system. in 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings., 6738651, pp. 3162-3166, 2013 20th IEEE International Conference on Image Processing, ICIP 2013, Melbourne, VIC, 15/9/13. https://doi.org/10.1109/ICIP.2013.6738651
Zulkifley MA, Mustafa MM, Hussain A. Probabilistic white strip approach to plastic bottle sorting system. In 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 3162-3166. 6738651 https://doi.org/10.1109/ICIP.2013.6738651
Zulkifley, Mohd Asyraf ; Mustafa, Mohd. Marzuki ; Hussain, Aini. / Probabilistic white strip approach to plastic bottle sorting system. 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. pp. 3162-3166
@inproceedings{7e62b040c47641c781bbd3d2e9fbe59e,
title = "Probabilistic white strip approach to plastic bottle sorting system",
abstract = "One of the most important steps in plastic recycling industry is waste sorting. Plastic wastes are usually sort into two main categories, which are polyethylene terephthalate (PET) and non-PET. This paper proposes a probabilistic approach to automated plastic bottle sorting by integrating size, colour and distance modelling of the plastic waste. Firstly, white strips are identified by employing maximum likelihood approach. Information on the white and grey strips is then analyzed by using maximum a posteriori method. Feature histogram is built by factoring the output decision of each white strip with its size. Finally, likelihood test is performed to classify the waste into PET and non-PET. Our algorithm performs the best in all evaluation metrics compared to the benchmark algorithms. It is most suitable to be implemented in a factory with the ever changing surroundings.",
keywords = "Likelihood test, Maximum a posteriori, Maximum likelihood classification, PET bottle identification, Plastic recycling",
author = "Zulkifley, {Mohd Asyraf} and Mustafa, {Mohd. Marzuki} and Aini Hussain",
year = "2013",
doi = "10.1109/ICIP.2013.6738651",
language = "English",
isbn = "9781479923410",
pages = "3162--3166",
booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

}

TY - GEN

T1 - Probabilistic white strip approach to plastic bottle sorting system

AU - Zulkifley, Mohd Asyraf

AU - Mustafa, Mohd. Marzuki

AU - Hussain, Aini

PY - 2013

Y1 - 2013

N2 - One of the most important steps in plastic recycling industry is waste sorting. Plastic wastes are usually sort into two main categories, which are polyethylene terephthalate (PET) and non-PET. This paper proposes a probabilistic approach to automated plastic bottle sorting by integrating size, colour and distance modelling of the plastic waste. Firstly, white strips are identified by employing maximum likelihood approach. Information on the white and grey strips is then analyzed by using maximum a posteriori method. Feature histogram is built by factoring the output decision of each white strip with its size. Finally, likelihood test is performed to classify the waste into PET and non-PET. Our algorithm performs the best in all evaluation metrics compared to the benchmark algorithms. It is most suitable to be implemented in a factory with the ever changing surroundings.

AB - One of the most important steps in plastic recycling industry is waste sorting. Plastic wastes are usually sort into two main categories, which are polyethylene terephthalate (PET) and non-PET. This paper proposes a probabilistic approach to automated plastic bottle sorting by integrating size, colour and distance modelling of the plastic waste. Firstly, white strips are identified by employing maximum likelihood approach. Information on the white and grey strips is then analyzed by using maximum a posteriori method. Feature histogram is built by factoring the output decision of each white strip with its size. Finally, likelihood test is performed to classify the waste into PET and non-PET. Our algorithm performs the best in all evaluation metrics compared to the benchmark algorithms. It is most suitable to be implemented in a factory with the ever changing surroundings.

KW - Likelihood test

KW - Maximum a posteriori

KW - Maximum likelihood classification

KW - PET bottle identification

KW - Plastic recycling

UR - http://www.scopus.com/inward/record.url?scp=84897747264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897747264&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738651

DO - 10.1109/ICIP.2013.6738651

M3 - Conference contribution

AN - SCOPUS:84897747264

SN - 9781479923410

SP - 3162

EP - 3166

BT - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

ER -