arrow
Volume 8, Issue 4
The Algorithm of ICA Based on PCA for Fabric Defect Detection

Junfeng Jing, Juan Zhao, Pengfei Li, Hongwei Zhang & Lei Zhang

Journal of Fiber Bioengineering & Informatics, 8 (2015), pp. 687-696.

Published online: 2015-08

Export citation
  • Abstract
The Independent Component Analysis (ICA) algorithm based on Principal Component Analysis (PCA) is described in this paper to achieve the raw textile defect detection. In the first step, the observed matrix X is constructed from a large number of defect-free sub-images and PCA is operated to achieve dimension reduction. In the second step, the transformation matrix W and independent basis subspace s are obtained from defect-free sub-images through ICA. In the final step, feature extraction is achieved from the overlapping sub-windows of a test image. Then a sub-window is classified as defective or nondefective according to Euclidean distance. The results have been analyzed in detail and illustrated this approach has better performance in raw textile.
  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JFBI-8-687, author = {Junfeng Jing, Juan Zhao, Pengfei Li, Hongwei Zhang and Lei Zhang}, title = {The Algorithm of ICA Based on PCA for Fabric Defect Detection}, journal = {Journal of Fiber Bioengineering and Informatics}, year = {2015}, volume = {8}, number = {4}, pages = {687--696}, abstract = {The Independent Component Analysis (ICA) algorithm based on Principal Component Analysis (PCA) is described in this paper to achieve the raw textile defect detection. In the first step, the observed matrix X is constructed from a large number of defect-free sub-images and PCA is operated to achieve dimension reduction. In the second step, the transformation matrix W and independent basis subspace s are obtained from defect-free sub-images through ICA. In the final step, feature extraction is achieved from the overlapping sub-windows of a test image. Then a sub-window is classified as defective or nondefective according to Euclidean distance. The results have been analyzed in detail and illustrated this approach has better performance in raw textile.}, issn = {2617-8699}, doi = {https://doi.org/10.3993/jfbim00166}, url = {http://global-sci.org/intro/article_detail/jfbi/4750.html} }
TY - JOUR T1 - The Algorithm of ICA Based on PCA for Fabric Defect Detection AU - Junfeng Jing, Juan Zhao, Pengfei Li, Hongwei Zhang & Lei Zhang JO - Journal of Fiber Bioengineering and Informatics VL - 4 SP - 687 EP - 696 PY - 2015 DA - 2015/08 SN - 8 DO - http://doi.org/10.3993/jfbim00166 UR - https://global-sci.org/intro/article_detail/jfbi/4750.html KW - Textile Defect Detection KW - Feature Extraction KW - Principal Component Analysis KW - Independent Component Analysis Heading KW - Introduction KW - Times New Roman KW - Number AB - The Independent Component Analysis (ICA) algorithm based on Principal Component Analysis (PCA) is described in this paper to achieve the raw textile defect detection. In the first step, the observed matrix X is constructed from a large number of defect-free sub-images and PCA is operated to achieve dimension reduction. In the second step, the transformation matrix W and independent basis subspace s are obtained from defect-free sub-images through ICA. In the final step, feature extraction is achieved from the overlapping sub-windows of a test image. Then a sub-window is classified as defective or nondefective according to Euclidean distance. The results have been analyzed in detail and illustrated this approach has better performance in raw textile.
Junfeng Jing, Juan Zhao, Pengfei Li, Hongwei Zhang and Lei Zhang. (2015). The Algorithm of ICA Based on PCA for Fabric Defect Detection. Journal of Fiber Bioengineering and Informatics. 8 (4). 687-696. doi:10.3993/jfbim00166
Copy to clipboard
The citation has been copied to your clipboard