Research on color solid built by gridded color mixing of nine primary colored fibers and its neural network color prediction approach

Abstract

According to the demand of color prediction for colored yarn, two adjacent colors chosen from red (R), yellow (Y), green (G), cyan (C), blue (B) and magenta (M) fibers were combined with fibers of dark gray (O¹), medium gray (O²) and light gray (O³), respectively, and then ternary coupling‐superposition mixing was performed to acquire a color solid consisting of three lightnesses, 18 color mixing units and 18×(m+1)×n grid points. An integrated color mixing with 20% hue gradient and 33.33% saturation gradient was performed to achieve a color solid containing 360 grid points and then using it as the sample space for the color prediction model. 360 typical samples were established by the grid points, 213 yarns and fabrics were prepared by the typical sample parameters, and the corresponding reflectance was accessed by spectrophotometer. Neural network models for predicting reflectance by mixing ratios as well as forecasting mixing ratios by reflectance were established. The 12 non‐grid point parameters were chosen to prepare corresponding yarns and fabrics, and the corresponding reflectance was measured. The predicted and measured values of the neural network model were compared to verify its predictive ability and generalizability. The results showed that: when predicting the color by the mixing ratios, the color difference between the predicted and measured samples ranged from 1.5 to 3.4, with an average of 2.4; when forecasting the mixing ratios by the color, the color difference ranged from 0.8 to 5.6, with an average of 2.4.

This article is protected by copyright. All rights reserved.