Colour Difference Classification for Dyed Fabrics Based on Differential Evolution with Dynamic Parameter Selection to Optimise the Output Regularisation Extreme Learning Machine

Abstract

A novel optimisation technique based on the differential evolution (DE) algorithm with dynamic parameter selection (DPS-DE) is proposed to develop a colour difference classification model for dyed fabrics, improve the classification accuracy, and optimise the output regularisation extreme learning machine (RELM). The technique proposed is known as DPS-DE-RELM and has three major differences compared with DE-ELM: (1) Considering that the traditional ELM provides an illness solution based on the output weights, DE is proposed to optimise the output of the RELM. (2) Considering the simple parameter setting of the traditional algorithm, the DE algorithm with DPS is adopted. (3) For DPS, an optimal range of parameters is chosen, and the efficiency of the algorithm is significantly improved. This study analyses the colour difference classification of fabric images captured under standard lighting based on the DPS-DE-RELM algorithm. First, the colour difference of the fabric images is calculated and six color-difference-related features extracted, and second the features are classified into five different levels based on the perception of humans. Finally, a colour difference classification model is built based on the DPS-DE-RELM algorithm, and then the optimal classification model suitable for this study is selected. The experimental results show that the output method with regularisation parameters can achieve a maximum classification accuracy of 98.87%, which is higher compared with the aforementioned optimised original ELM algorithm, which can achieve a maximum accuracy of 84.67%. Therefore, the method proposed has the advantages of greater convergence speed, high classification accuracy, and robustness.