Using compound microscopy is one of the major options for the identification of cashmere/wool. To interpret human perception via machine vision, microscopic images captured by a charge-coupled device camera were transferred into projection curves. Three different deciphering methods, recurrence quantification analysis, direct geometrical description, and discrete wavelet transform were employed to reveal the embedded numerical features. The extracted parameters were used to screen the supervised classification methods, including a neural network with multilayer perceptrons, kernel ridge regression/classification, and the support vector machine (SVM). The experimental results indicated that the proposed projection curves could be used as a mathematical replica in automatic cashmere/wool identification. The best accuracy came from a SVM-trained decision function with the parameters extracted from recurrence quantification analysis.
KerkhoffKCescuttiGKruseLet al.Development of a DNA-analytical method for the identification of animal hair fibers in textiles. Text Res J2009; 79: 69–75.
2.
McGregorBA. Variation in the softness and fibre curvature of cashmere, alpaca, mohair and other rare animal fibres. J Text Inst2014; 105: 597–608.
3.
ReinholdK. Cashmere has been taken by surprise. Textil-wirtschaft2001; 16: 61–62.
4.
Van NiekerkWAKevaSRoetsMet al.The accuracy of Video Image Analysis (VIA) and Optical Fibre Diameter Analysis (OFDA) to measure fibre diameter of cashmere. South African Journal of Animal Science2004; 34: 143–144.
5.
TangMZhangWZhouHet al.A real-time PCR method for quantifying mixed cashmere and wool based on hair mitochondrial DNA. Text Res J2014; 84: 1612–1621.
6.
Phan KH and Wortmann FJ. Cashmere definition and analysis: scientific and technical status. In: The 3rd international symposium on specialty fibres, DWI Aachen, Germany, 2004.
7.
McGregorBA. Influence of nutrition, fibre diameter and fibre length on the fibre curvature of cashmere. Anim Prod Sci2003; 43: 1199–1209.
8.
McGregorBA. Cashmere fibre crimp, crimp form and fibre curvature. Int J Sheep Wool Sci2007; 55: 106–129.
9.
McGregorBAButlerKL. The effects of cashmere attributes on the efficiency of dehairing and dehaired cashmere length. Text Res J2008; 78: 486–496.
10.
McGregorBAButlerKL. Implications to fleece evaluation derived from sources of variation contributing to cashmere fibre curvature. Small Ruminant Res2009; 81: 1–7.
11.
Ma HY, Tian ZF, Hong X, et al. Analysis on cashmere quality and morphology changes in different places of origin. Report, Erdos Group, China, July 2015.
12.
HeLZChenLPWangXM. Detection methods of distinguishing cashmere and wool fibers. Prog Text Sci Technol2008; 2: 27–27.
13.
ShengGZLiL. Study on distinguishing problem of cashmere fiber. Wool Text J2007; 12: 52–54.
14.
YangGFFuYHongXet al.Discussion on the SEM/OM in cashmere identification. China Fiber Inspect2006; 6: 17–20.
15.
ZoccolaMLuNMossottiRet al.Identification of wool, cashmere, yak, and Angora rabbit fibers and quantitative determination of wool and cashmere in blend: A near infrared spectroscopy study. Fibers Polym2013; 14: 1283–1289.
16.
SebastianiF. Machine learning in automated text categorization. ACM Comput Surv2002; 34: 1–47.
17.
AcharyaURSreeSVChattopadhyaySet al.Application of recurrence quantification analysis for the automated identification of epileptic EEG signals. Int J Neural Syst2011; 21: 199–211.
18.
Alpaydin E. Introduction to machine learning. Cambridge: MIT Press, 2014, p.71.
19.
Rutkin A. Anything you can do …. New Sci 2016, 229: 20–21.
20.
WangBHHuZYGeSSet al.Identification of wool and cashmere based on light microscope. Wool Text J2011; 39: 42–45.
21.
Shi XJ and Yu WD. Identification of animal fiber based on scale shape. In: 1st international congress on image and signal processing, Sanya, China, 27–30 May, 2008, pp.573-577.
22.
MurphyKP. Machine learning: A probabilistic perspective, Cambridge: MIT Press, 2012, pp. 492–493.
23.
HaykinSS. Neural networks and learning machines, Upper Saddle River, NJ: Pearson Education, 2009, pp. 103–104.
Tong S and Chang E. Support vector machine active learning for image retrieval. In: Proceedings of the ninth ACM international conference, Ottawa, Canada, 30 September–5 October, 2001, pp.107–118. New York: ASME.
26.
Tsochantaridis I, Hofmann T, Joachims T, et al. Support vector machine learning for interdependent and structured output spaces. In: Proceedings of the twenty-first international conference on Machine learning, Banff, Canada, 4–8 July, 2004, pp.104–111. New York: ACM.
27.
AnSLiuWVenkateshS. Fast cross-validation algorithms for least squares support vector machine and kernel ridge regression. Pattern Recog2007; 40: 2154–2162.
28.
WangRWWuXYWangSYet al.Automatic identification of ramie and cotton fibers using characteristics in longitudinal view, part II: fiber stripes analysis. Text Res J2009; 79: 1547–1556.
29.
GonzalesRCWoodsR. Digital image processing, Boston, MA: Addison Wesley, 1992, pp. 443–452.
30.
HaralickRMShapiroLG. Computer and robot vision, Boston, MA: Addison Wesley, 1992, pp. 346–351.
31.
JainAK. Fundamentals of digital image processing, London: Prentice Hall, 1989, pp. 213–235.
32.
Jakkula V. Tutorial on support vector machines. School of EECS Washington State University, Pullman 99164, 2011.
33.
Bracewell R. Heaviside's unit step function, H(x). The Fourier transform and its applications. 3rd ed. New York: McGraw-Hill, 2000, pp.61–65.
34.
WebberCLJrZbilutJPRecurrence quantification analysis of nonlinear dynamical systems. In: RileyMAVan OrdenGC (eds). Tutorials in contemporary nonlinear methods for the behavioral sciences, Arlington, VA: National Science Foundation, 2005, pp. 26–94.
35.
BurrusCSGopinathRAGuoH. Introduction to wavelets and wavelet transforms. Radiographics1998; 18: 469–481.
36.
OcakH. Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy. Expert Syst Appl2009; 36: 2027–2036.
37.
ArelIRoseDCKarnowskiTP. Deep machine learning-a new frontier in artificial intelligence research. IEEE Comput Intell Mag2010; 5: 13–18.
38.
He K, Zhang X, Ren S, et al. Deep residual learning for image recognition, http://arxiv.org/abs/1512.03385 (2015, accessed on 10 February 2016).
