2018
DOI: 10.1002/col.22262
|View full text |Cite
|
Sign up to set email alerts
|

Illumination correction of dyed fabrics method using rotation forest‐based ensemble particle swarm optimization and sparse least squares support vector regression

Abstract: Different illuminations adversely affect color difference evaluation of textile images in dyed fabrics. To address the problem, we propose a rotation forest (RF)‐based ensemble particle swarm optimization and sparse least squares support vector regression (RF‐PSO‐SLSSVR) for building an accurate illumination correction model. In our algorithm, grey‐edge is first used to extract the statistics characteristics of the textile image. Second, as the standard LSSVR cannot yield a sparse solution, we develop sparse L… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
8
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 12 publications
(9 citation statements)
references
References 35 publications
0
8
0
Order By: Relevance
“…When the inertia weight is small, the local search ability of the algorithm is stronger, which enables fine searching around the optimal solution to speed up the convergence speed. To solve the problem of slower algorithm convergence speed, inspired by Reference 16, this study proposes a new adaptive weight method. The adaptive weight formula is shown in Equation ), and the improved ) is shown as Equation ): 0.25emγ=sin()πt2Max_it+π+10.25em true0.25emX0.25em()t+1=γtrue0.25emX*()ttrueA0.25emtrueD0.25em where t is the current number of iterations, and Max_it is the maximum number of iterations.…”
Section: Preliminariesmentioning
confidence: 99%
See 1 more Smart Citation
“…When the inertia weight is small, the local search ability of the algorithm is stronger, which enables fine searching around the optimal solution to speed up the convergence speed. To solve the problem of slower algorithm convergence speed, inspired by Reference 16, this study proposes a new adaptive weight method. The adaptive weight formula is shown in Equation ), and the improved ) is shown as Equation ): 0.25emγ=sin()πt2Max_it+π+10.25em true0.25emX0.25em()t+1=γtrue0.25emX*()ttrueA0.25emtrueD0.25em where t is the current number of iterations, and Max_it is the maximum number of iterations.…”
Section: Preliminariesmentioning
confidence: 99%
“…Because the decision function obtained by the least squares support vector regression (LSSVR) algorithm is related to all learning samples, it loses the sparseness of the traditional SVR algorithm solution. Accordingly, Zhou et al 16 proposed an illumination correction model based on the rotating forest‐based integrated particle swarm optimization and sparse LSSVR, which resolved the sparse solution problem by extracting the maximal independent subset of samples of the input vector in the feature space, thereby obtaining the RF‐PSO‐SLSSVR illumination correction model with a strong generalization ability. Recently, research on illumination correction has also continued to take place.…”
Section: Introductionmentioning
confidence: 99%
“…Different illuminations adversely affect color difference evaluation of textile images in dyed fabrics. Therefore, an integrated particle swarm optimization based on rotating forest (RF) and sparse least square support vector regression (RF-PSO-SLSSVR) was proposed to establish an accurate illumination correction model (Zhou et al 2019). In addition to the lighting conditions, the factors affecting chromatic aberration also need to be classified.…”
Section: Calculation Of Color Differencementioning
confidence: 99%
“…However, the selection of the kernel function of the support vector machine and the calculation of the parameters increases the computational complexity of the algorithm. In order to optimize the selection of support vector machine kernel function and the calculation of parameters, Zhou et al 5 proposed using Particle Swarm Optimization (PSO) technology to optimize the regularization parameters and kernel parameters of the sparse least squares support vector regression (SLSSVR), which improves the prediction accuracy of the base learner. Finally, the weighted average method is used to fuse the trained PSO-SLSSVR submodels to form a robust improved least squares support vector machine as the illumination estimation model for printing and dyeing products.…”
Section: Introductionmentioning
confidence: 99%