Objective rating of fabric wrinkles via random vector functional link based on the improved salp swarm algorithm

Abstract

To solve the problem of inefficiency and inaccuracy associated with the classification of fabric wrinkles by human eyes, as well as improve current deficiencies in the application of neural networks for the classification of fabric wrinkles, we propose a model based on the salp swarm algorithm improved by ant lion optimization to optimize the random vector functional link to objectively evaluate the fabric wrinkle level. First, to improve the global searchability of the salp swarm algorithm and avoid the local optima problem, the use of ant lion optimization to improve the salp swarm algorithm is proposed in this study. Afterward, the improved salp swarm algorithm is used to optimize the input weight and hidden layer bias of the random vector functional link to avoid the inaccuracy and instability of random vector functional link classification owing to the randomness of the parameters. Finally, the performance of the proposed algorithm is verified using a fabric wrinkle dataset. Comparative experiments show that the classification accuracy of the proposed ant lion optimization - salp swarm algorithm - random vector functional link algorithm were 8.46%, 2.05%, 10.28%, 3.50%, and 4.42% higher than those of random vector functional link, improved random vector functional link based on salp swarm algorithm, extreme learning machine, improved extreme learning machine based on whale optimization algorithm, and improved backpropagation based on the Levenberg-Marquardt algorithm. Furthermore, the classification accuracy of the wrinkle level was effectively improved. All the fabrics used in this study were monochromatic, and multi-color printed fabrics have a significant impact on the difficulty of image processing and classification results. The next research step is to evaluate the wrinkle level of multi-color printed fabrics.

Keywords

Classification of fabric wrinkles ant lion optimization salp swarm algorithm random vector functional link

Get full access to this article

View all access options for this article.

References

Tsunehiro

Takehiro

Masanori

Automatic evaluation of the appearance of seam puckers on suits. IEICE T Inf Sys 2000; 7: 1346–1352.

Mohri

Ravandi

SAH

Youssefi

Objective evaluation of wrinkled fabric using radon transform. J Text I 2005; 96: 365–370.

Ravanidi

SAH

Pan

The influence of gray-level co-occurrence matrix variables on the textural features of wrinkled fabric surfaces. J Text I 2011; 102: 315–321.

Liu

NY.

Novel testing equipment for fabric wrinkle resistance simulating actual wear. Text Res J 2014; 84: 1059–1069.

Urbiola-Soto

Lopez

Instrumentation system for objective evaluation of wrinkle appearance in fabrics using a standardized inspection booth. Text Res J 2014; 84: 368–387.

Liu

CY.

Comparative investigation on objective evaluation methods of fabric smoothness.

Fibres Text East Eur 2020; 28: 43–49.

Sun

Yao

BG.

Fabric wrinkle characterization and classification using modified wavelet coefficients and support-vector-machine classifiers. Text Res J 2011; 81: 902–913.

Zhang

Yang

Evaluation model of color difference for dyed fabrics based on the Support Vector Machine. Text Res J 2014; 84: 2184–2197.

Liu

Zuo

BQ.

Identification of fabric defects based on discrete wavelet transform and back-propagation neural network. J Text I 2007; 98: 355–362.

10.

Kuo

CFJ

Lee

CJ.

A back-propagation neural network for recognizing fabric defects. Text Res J 2003; 73: 147–151.

11.

Zhang

Satapath

SC.

Improved breast cancer classification through combining graph convolutional network and convolutional neural network.

Inform Process Manag 2021; 58 Article ID: 102439.

12.

Wang

Govindaraj

VV.

Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network. Inform Fusion 2021; 67: 208–229.

13.

Huang

Zhou

Ding

, et al . Extreme learning machine for regression and multiclass classification. IEEE T Syst 2012; 42: 513–529.

14.

Huang

Zhu

Siew

CK.

Extreme learning machine: theory and applications. Neurocomputing 2006; 70: 489–501.

15.

Huang

Zhu

Siew

CK.

Extreme learning machine: a new learning scheme of feed forward neural networks. IEEE Int Jt Conf Neural Netw 2005; 2: 985–990.

16.

Pradhan

Minz

Shrivastava

VK.

Fast active learning for hyperspectral image classification using extreme learning machine. IET Image Process 2019; 13: 549–555.

17.

Xiong

A supervised combination strategy for illumination chromaticity estimation. ACM T Appl Percept 2010; 8: 1–17.

18.

Mirjalili

Moth-flame optimization algorithm: a novel nature-inspired heuristic paradigm.

Knowl Based Syst 2015; 89: 228–249.

19.

Mirjalili

Lewis

The whale optimization algorithm. Adv Eng Softw 2016; 95: 51–67.

20.

Mirjalili

Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems. Neural Comput Appl 2016; 27: 1053–1073.

21.

Heidari

Mirjalili

Faris

Harris hawks optimization: algorithm and applications. Future Gener Comp Sy 2019; 97: 849–872.

22.

Mirjalili

The ant lion optimizer. Adv Eng Softw 2015; 83: 80–98.

23.

Zhou

Wang

Zhang

, et al. Color difference classification of solid color printing and dyeing products based on optimization extreme learning machine of improved whale optimization algorithm. Text Res J 2019; 90: 135–155.

24.

Mohapatra

Chakravarty

Dash

PK.

An improved cuckoo search based extreme learning machine for medical data classification. Swarm Evol Comput 2015; 24: 25–49.

25.

Sanchez-Monedero

Hervds-Martinez

Gutierrez

PA.

Evaluating the performance of evolutionary extreme learning machines by a combination of sensitivity and accuracy measures. Neural Netw World 2010; 20: 899–912.

26.

Kong

Chen

Tool wear estimation in end-milling of titanium alloy using NPE and a novel WOA-SVM model. IEEE T Instrum Meas 2019; 69: 5219–5232.

27.

Fan

Wang

Heidari

AA.

Rationalized fruit fly optimization with sine cosine algorithm: a comprehensive analysis. Expert Syst Appl 2020; 157: 113486.

28.

Elaziz

Hemedan

Ostaszweski

Optimization ACE inhibition activity in hypertension based on random vector functional link and sine-cosine algorithm. Chemometr Intell Lab 2019; 190: 69–77.

29.

Mirjalili

Gandomi

Mirjalili

SZ.

Salp swarm algorithm: a bio-inspired optimizer for engineering design problems. Adv Eng Softw 2017; 114: 163–191.