Computer vision-based color sorting for waste textile recycling
International Journal of Clothing Science and Technology
ISSN: 0955-6222
Article publication date: 17 February 2021
Issue publication date: 1 March 2022
Abstract
Purpose
Efficient and high-accuracy intelligent color and material sorting systems are the main bottlenecks restricting the recycling of waste textiles. The mixing of waste textiles with different colors will make the reconstructed raw material of textile fiber useless or with low quality. In this study, some challenges about the automatic color sorting for waste textile recycling are discussed. A computer vision-based color sorting system for waste textile recycling is introduced, which can classify the required colors well and meet the efficiency requirements of an automatic recycling line.
Design/methodology/approach
There are four aspects, (1) two cameras with different exposure times and white-balance parameters are involved for establishing the computer vision system. (2) Two standard color databases with two cameras are constructed. (3) A statistical model to determine the colors of textile samples is presented in which uniform sampling of pixels and mid-tone enhancing techniques are exploited. (4) The experiments with a number of waste textile samples from a factory in Hong Kong are conducted to illustrate the efficiency of the developed system.
Findings
The experiments with a number of waste textile samples from a factory in Hong Kong are reported. The total classification accuracy performs good. The research methods and results reported in this study can provide an important reference for improving the intelligent level of color sorting for waste textile recycling.
Originality/value
It is the first time to introduce computer vision technology to a color sorting system for recycling waste textiles, especially in a real recycling factory in Hong Kong. The research methods and results reported in this study also deliver guidance for designing a computer vision-based color sorting system for other industrial scenarios.
Keywords
Acknowledgements
The authors are grateful to the anonymous referees for their valuable comments and suggestions. They also thank Mr. John Leung and Dr. Can Gao for their kind discussions. This work is supported by the National Natural Science Foundation of China (No. 62076164) and the Guangdong Natural Science Foundation (No. 2018A030310450).
Citation
Zhou, J., Zou, X. and Wong, W.K. (2022), "Computer vision-based color sorting for waste textile recycling", International Journal of Clothing Science and Technology, Vol. 34 No. 1, pp. 29-40. https://doi.org/10.1108/IJCST-12-2019-0190
Publisher
:Emerald Publishing Limited
Copyright © 2021, Emerald Publishing Limited