Cashmere and wool play an important role in the wool industry and textile industry, and suitable features are the key to identifying them. To obtain effective features and improve the accuracy of cashmere and wool classification, the multi-feature selection and random forest method is used to express in this article. Firstly, the gray-gradient co-occurrence matrix model is used for texture feature extraction to construct the original high-dimensional feature data set; secondly, considering that the original feature data set contains a large number of invalid and redundant features, the feature selection algorithm combining correlation analysis and principal component analysis–weight coefficient evaluation is used to obtain important features, independent features, and principal component sensitive features to complement each other; last but not least, the optimized random forest model analyzes the results. The results show that the combination of multi-feature selection subsets and random forest makes the classification accuracy of cashmere and wool more reliable, and the accuracy fluctuates around 90%.
XingWDengNXinB, et al.
Identification of extremely similar animal fibers based on matched filter and HOG-SVM. IEEE Access2019;
7: 98603–98617.
2.
Xing W, Deng N, Xin B, et al. Investigation of a novel automatic micro image-based method for the recognition of animal fibers based on Markov Random Field. Micron 2019; 119: 88–97.
3.
Xing W, Liu Y, Deng N, et al. Automatic identification of cashmere and wool fibers based on the morphological features analysis. Micron 2020; 128. doi: https://doi.org/10.1016/j.micron.2019.102768.
4.
ShiXYuW, et al.An identification method for cashmere and fine wool based on Bayes model. J Text Res2008;
29: 26–29.
5.
ZhuJLuKChaiX, et al.Level set of central axis method of cashmere and wool diameter. J Text Res2017;
38: 14–18.
6.
Peng W and Jiang Y. The analysis of shape feature of cashmere and fine wool. Shanghai Text Sci Technol 2005; 33: 11-12+16.
7.
ZhouJFengJ, et al.Automatic recognition method for wool fiber images of an electron microscope. J Image Graph2001;
10: 37–41.
8.
Yang J and Wang R. Image processing and identify of surface structure of cashmere and wool. Wool Text J 2002; 05: 12–15.
9.
ShiXHuX, et al.Theoretical recognition accuracy and error rate for cashmere based on scale pattern gene code. J Text Res2014;
35: 5–10.
10.
ShiXHuX, et al.Distribution and correlation of scale pattern gene codes for cashmere. J Text Res2014;
35: 1–5.
11.
JiYYangYHuangS.Identification of wool and cashmere based on decision tree algorithm. J Text Res2013;
34: 16–20.
12.
XieJYuW.Using the scale pattern to identify the cashmere and determine its content. J Donghua Univ (Nat Sci)2013;
39: 737–743.
13.
LiuXMaCLiuF, et al.Cashmere recognition based on optical image feature. Wool Text J2014;
42: 57–62.
14.
YuanSLuKZhongK.Identification of wool and cashmere based on texture analysis. Key Eng Mater2016;
671: 385–390.
15.
LiGZhongY, et al.Identification of wool and cashmere based on the analysis of the spectral line. Wool Text J2010;
38: 38–41.
16.
Zhong Y, Lu K, et al. Wool/cashmere identification based on projection curves. Text Res J 2017; 87(14): 1730–1741.
17.
LuKZhongYLiD, et al.
Cashmere/wool identification based on bag-of-words and spatial pyramid. Text Res J2018;
88: 2435–2444.
18.
JiaoM.A cashmere and wool recognition method based on gray level co-occurrence matrix. J Chengdu Text Coll2017;
34: 126–129.
19.
ChaiXLuK, et al.Identification algorithm of wool and cashmere based on SURF feature. Shanghai Text Sci Technol2018;
46: 25–29.
20.
ZhouJFengJ, et al.Automatic recognition method for wool fiber images of an electron microscope. J Image Graph2001;
10: 37–41.
21.
PanHGaoP, et al.
Roughness analysis of sea surface from visible images by texture. Spec Sect Integr Comput Vis Multimed Analyt2020;
8: 46448–46458.
22.
XiaoDWangRZhouX, et al.
A noninvasive temperature measurement based on Gabor transform and gray level gradient co-occurrence matrix using ultrasound. J Transduct Technol2017;
30: 1684–1688.
23.
ZhaiAWenXZhangX.Retrieval algorithm for texture image based on improved dual tree complex wavelet transform and gray-gradient co-occurrence matrix. Comput Sci2017;
44: 274–277.
24.
HariharanSMandalDTirodkarS, et al.
A novel phenology based feature subset selection technique using random forest for multitemporal PolSAR crop classification. IEEE J Select Topic Appl Earth Observ Remote Sens2018;
11: 4244–4258.
25.
LiYDaiW, et al.
Bearing fault feature selection method based on weighted multidimensional feature fusion. IEEE Access2020;
8: 19008–19024.
26.
ZhangH, et al.
Image classification using rapid eye data: integration of spectral and textual features in a random forest classifier. IEEE J Select Topic Appl Earth Observ Remote Sens2017;
10: 5334–5349.
27.
PiaoJDenH, et al.Analysis of preprocessing method of cashmere image based on MATLAB. Light Text Ind Technol2015;
44: 1–5.
28.
LingYZhongJ, et al.The principle and application of scanning electron microscope. Shandong Chem Ind2018;
47: 78–79 + 83.
29.
XiaoDWangRZhouX, et al.A noninvasive temperature measurement based on Gabor transform and gray level gradient co-occurrence matrix using ultrasound. J Transduct Technol2017;
30: 1684–1688.
30.
Breiman L. Random forests. Mach Learn 2001; 45: 5–32.
31.
JiXYangB, et al. Seabed sediment classification using multibeam backscatter data based on the selecting optimal random forest model. Applied Acoustics 2020; 167. doi:10.1016/j.apacoust.2020.107387.
32.
XiaJLiaoWChanussotJ, et al.Improving random forest with ensemble of features and semisupervised feature extraction. IEEE Geo Sci Remote Sens Lett2015;
12: 1471–1475.
33.
Xue G, Li X, Qian X, et al. Coal-gangue image recognition in fully-mechanized caving face based on random forest. Ind Mine Automat 2020; 46(05): 57–62.
