TY - JOUR
T1 - Regression Analysis on Tie-dye Technique and Pattern Feature
AU - Suqiong Liu , HuieLiang, Weidong Gao, Wei Xue & Ming Gu
JO - Journal of Fiber Bioengineering and Informatics
VL - 4
SP - 561
EP - 571
PY - 2014
DA - 2014/07
SN - 7
DO - http://doi.org/10.3993/jfbi12201409
UR - https://global-sci.org/intro/article_detail/jfbi/4810.html
KW - Tie-dye
KW - Image Processing
KW - HSV
KW - Regression Analysis
AB - Based on computer vision technology, we studied predictive method of tie-dye pattern information.
We extracted the average value of HSV (hue, saturation, value) tri-component of valid tie-dye area,
proportion of tie-dye white area and coarseness as pattern feature, and designed correlation analysis on
tie-dye production process and pattern feature accordingly. The results showed that dye concentration
and pattern feature are highly correlated and the speed is also an important indicator of the effect of tie-
dye pattern. In view of tie-dye production speed, concentration process parameters and pattern feature
linear regression analysis, the findings are as follows: there is a positive correlation between process
parameters and H, S component mean; process parameters negatively correlate with V component mean
and proportion of tie-dye white area and coarseness; R-Squared values of prediction model are greater
than 0.5. The linear regression models can be used to predict tie-dye image pattern effects.