Color spectra algorithm of hyperspectral wood dyeing using particle swarm optimization
- PDF / 1,172,687 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 70 Downloads / 218 Views
Color spectra algorithm of hyperspectral wood dyeing using particle swarm optimization Machao Wu1 · Xuemei Guan1 · Wenfeng Li1 · Qinglong Huang1 Received: 21 May 2020 / Accepted: 5 October 2020 © The Author(s) 2020
Abstract To improve the accuracy and practicality of the intelligent color-matching application of wood dyeing technology, Fraxinus mandshurica veneer was selected as the dyeing material. First, based on the Friele model and Stearns–Noechel model, the model parameters were cyclically assigned to calculate the optimal fixed parameter values and predictions. Then, particle swarm algorithm was used to optimize two algorithm models, the obtained reflectance curve was fit, and the color differences were calculated according to the human eye-based CIEDE2000 color difference evaluation standard formula. Last, the two formulas to predict the color difference and spectral reflectance were compared. First, the two optimization algorithms were compared according to the size of the fitted color difference value, and then, the most accurate optimization algorithm was selected. When the model parameters were fixed, the average fitted color difference was 0.8202. After optimizing the Friele model, the average fitted color difference was 0.7287, and after optimizing the Stearns–Noechel model, the average fitted color difference was 0.6482. It was concluded that the improved Stearns–Noechel model based on particle swarm method was more accurate than the Friele model for wood color matching.
Introduction To achieve efficient use of plantation forests, the computer-assisted dyeing and color-matching technologies are used to improve inferior materials and imitate valuable materials (Guan 2011; Guan et al. 2010). Using the method based on Bayesian normalization algorithm and Levenberg–Marquardt (LM) algorithm to improve the traditional BP neural network has improved the accuracy of the simulation concentration and the generalization of the network (Nie et al. 2008), but the network convergence speed has not been significantly improved, and the training sample size is * Machao Wu [email protected] 1
College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China
13
Vol.:(0123456789)
Wood Science and Technology
large. Based on the application of the improved RBF neural network in wood dyeing and color-matching technology, the generalization ability of the network is gradually improved to a certain extent (Guan et al. 2016). In traditional algorithms, evolutionary calculations in swarm intelligence are used to improve various problems in neural network modeling, aiming to solve the local limit problem of traditional BP neural networks in learning and training (Ji 2013), which can improve the learning accuracy. The convergence speed, to a certain extent, is superior to conventional neural network learning algorithms. The fixed parameters are set based on the Friele model, and different methods are used to predict and fit the reflectance and the reflection formula to obtain a c
Data Loading...
