Search results

1 – 2 of 2
Click here to view access options
Article
Publication date: 17 February 2021

Jie Zhou, Xingxing Zou and Wai Keung Wong

Efficient and high-accuracy intelligent color and material sorting systems are the main bottlenecks restricting the recycling of waste textiles. The mixing of waste…

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.

Details

International Journal of Clothing Science and Technology, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 0955-6222

Keywords

Click here to view access options
Article
Publication date: 28 June 2019

Xingxing Zou, Wai Keung Wong, Can Gao and Jie Zhou

The deficiency of the mapping between fashion color (FoCo) value and linguistic color expression causes the difficulty of machine-based fashion understanding tasks that…

Abstract

Purpose

The deficiency of the mapping between fashion color (FoCo) value and linguistic color expression causes the difficulty of machine-based fashion understanding tasks that are heavily associated with color matching. The purpose of this paper is to propose the FoCo system and construct it with four steps, in order to bridge this gap.

Design/methodology/approach

The color distribution in HSB color space is analyzed to estimate the rough number of color categories. Similar color values are grouped to obtain the initial HSB value range for each color category. The intra-category color differences are calculated to determine their final HSB value ranges and Pantone color is used for fine-tuning.

Findings

With practical applications in mind, the FoCo system is designed as a hierarchical structure with three layers.

Originality/value

The FoCo system is designed as a hierarchical structure with three layers: color units for color matching-related tasks, color categories for style analysis tasks and color tones for color recognition tasks. Extensive experiments demonstrate the effectiveness of the FoCo system.

Details

International Journal of Clothing Science and Technology, vol. 31 no. 5
Type: Research Article
ISSN: 0955-6222

Keywords

1 – 2 of 2