arrow
Volume 9, Issue 1
Study on Automatic Recognition of Fabric Color and Matching to Standard Color Chip by Computer Vision and Image Analysis Technology

Liqing Xie, Yue Shen & Xiaozhi Chen

Journal of Fiber Bioengineering & Informatics, 9 (2016), pp. 29-37.

Published online: 2016-02

Export citation
  • Abstract
The Artificial visual approach to detect fabric color is easy to be affected by light and experience. In order to overcome the shortcomings of errors, this paper presents a new method for matching between textile fabric color and standard color card automatically, and establishes the automatic matching system for 1925 kinds of Pantone TCX color swatches by using computer vision and image analysis. First, the scan images of Pantone TCX color were acquired, then we extracted effective color characteristic information from the images, and constructed the database of color features. Furthermore, we designed color layered model and matching model which based on ‘one to one’ Support Vector Machine (SVM). Through parameter optimization and identify training for SVM model, the accuracy of color identifying is 96.89%. Finally, we used 296 unknown color samples for verification, the accuracy is 98.85%. The results show that the research provides an effective auxiliary tool objectively and quickly for color measurement.
  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JFBI-9-29, author = {Liqing Xie, Yue Shen and Xiaozhi Chen}, title = {Study on Automatic Recognition of Fabric Color and Matching to Standard Color Chip by Computer Vision and Image Analysis Technology}, journal = {Journal of Fiber Bioengineering and Informatics}, year = {2016}, volume = {9}, number = {1}, pages = {29--37}, abstract = {The Artificial visual approach to detect fabric color is easy to be affected by light and experience. In order to overcome the shortcomings of errors, this paper presents a new method for matching between textile fabric color and standard color card automatically, and establishes the automatic matching system for 1925 kinds of Pantone TCX color swatches by using computer vision and image analysis. First, the scan images of Pantone TCX color were acquired, then we extracted effective color characteristic information from the images, and constructed the database of color features. Furthermore, we designed color layered model and matching model which based on ‘one to one’ Support Vector Machine (SVM). Through parameter optimization and identify training for SVM model, the accuracy of color identifying is 96.89%. Finally, we used 296 unknown color samples for verification, the accuracy is 98.85%. The results show that the research provides an effective auxiliary tool objectively and quickly for color measurement.}, issn = {2617-8699}, doi = {https://doi.org/10.3993/jfbim00194}, url = {http://global-sci.org/intro/article_detail/jfbi/10589.html} }
TY - JOUR T1 - Study on Automatic Recognition of Fabric Color and Matching to Standard Color Chip by Computer Vision and Image Analysis Technology AU - Liqing Xie, Yue Shen & Xiaozhi Chen JO - Journal of Fiber Bioengineering and Informatics VL - 1 SP - 29 EP - 37 PY - 2016 DA - 2016/02 SN - 9 DO - http://doi.org/10.3993/jfbim00194 UR - https://global-sci.org/intro/article_detail/jfbi/10589.html KW - Fabric Color KW - Color Matching KW - Image Processing KW - Support Vector Machine (SVM) KW - Pantone Color Swatches AB - The Artificial visual approach to detect fabric color is easy to be affected by light and experience. In order to overcome the shortcomings of errors, this paper presents a new method for matching between textile fabric color and standard color card automatically, and establishes the automatic matching system for 1925 kinds of Pantone TCX color swatches by using computer vision and image analysis. First, the scan images of Pantone TCX color were acquired, then we extracted effective color characteristic information from the images, and constructed the database of color features. Furthermore, we designed color layered model and matching model which based on ‘one to one’ Support Vector Machine (SVM). Through parameter optimization and identify training for SVM model, the accuracy of color identifying is 96.89%. Finally, we used 296 unknown color samples for verification, the accuracy is 98.85%. The results show that the research provides an effective auxiliary tool objectively and quickly for color measurement.
Liqing Xie, Yue Shen and Xiaozhi Chen. (2016). Study on Automatic Recognition of Fabric Color and Matching to Standard Color Chip by Computer Vision and Image Analysis Technology. Journal of Fiber Bioengineering and Informatics. 9 (1). 29-37. doi:10.3993/jfbim00194
Copy to clipboard
The citation has been copied to your clipboard