Automatic Classification of Woven Fabric Structure Based on Computer Vision Techniques
DOI:
10.3993/jfbi03201507
Journal of Fiber Bioengineering & Informatics, 8 (2015), pp. 69-79.
Published online: 2015-08
Cited by
Export citation
- BibTex
- RIS
- TXT
@Article{JFBI-8-69,
author = {Xuejuan Kang, Mengmeng Xu and Junfeng Jing},
title = {Automatic Classification of Woven Fabric Structure Based on Computer Vision Techniques},
journal = {Journal of Fiber Bioengineering and Informatics},
year = {2015},
volume = {8},
number = {1},
pages = {69--79},
abstract = {Traditionally woven fabric structure classification is based on manual work in textile industry. This paper
proposes an automatic approach to classify the three woven fabrics: plain, twill and satin weave. Firstly
2-D wavelet transform is used to obtain low frequency sub-image in order to reduce the analysis of fabric
images. Then graylevel co-occurrence matrix (GLCM) and Gabor wavelet are adopted to extract the
texture features of pre-processing fabric images. Finally Probabilistic Neural Network (PNN) is applied
to classify the three basic woven fabrics. The experimental results demonstrate that the proposed method
can automatically, efficiently classify woven fabrics and obtain accurate classification results (93.33%).},
issn = {2617-8699},
doi = {https://doi.org/10.3993/jfbi03201507},
url = {http://global-sci.org/intro/article_detail/jfbi/4687.html}
}
TY - JOUR
T1 - Automatic Classification of Woven Fabric Structure Based on Computer Vision Techniques
AU - Xuejuan Kang, Mengmeng Xu & Junfeng Jing
JO - Journal of Fiber Bioengineering and Informatics
VL - 1
SP - 69
EP - 79
PY - 2015
DA - 2015/08
SN - 8
DO - http://doi.org/10.3993/jfbi03201507
UR - https://global-sci.org/intro/article_detail/jfbi/4687.html
KW - Woven Fabric Structure
KW - Automatic Classification
KW - 2-D Wavelet Transform
KW - GLCM
KW - Gabor Wavelet
KW - PNN
AB - Traditionally woven fabric structure classification is based on manual work in textile industry. This paper
proposes an automatic approach to classify the three woven fabrics: plain, twill and satin weave. Firstly
2-D wavelet transform is used to obtain low frequency sub-image in order to reduce the analysis of fabric
images. Then graylevel co-occurrence matrix (GLCM) and Gabor wavelet are adopted to extract the
texture features of pre-processing fabric images. Finally Probabilistic Neural Network (PNN) is applied
to classify the three basic woven fabrics. The experimental results demonstrate that the proposed method
can automatically, efficiently classify woven fabrics and obtain accurate classification results (93.33%).
Xuejuan Kang, Mengmeng Xu and Junfeng Jing. (2015). Automatic Classification of Woven Fabric Structure Based on Computer Vision Techniques.
Journal of Fiber Bioengineering and Informatics. 8 (1).
69-79.
doi:10.3993/jfbi03201507
Copy to clipboard