Wool and cashmere are very similar in their morphological characteristics, physical and chemical properties, and composition, which brings great difficulties and challenges to their identification. The existing methods have two shortcomings: they are insensitive to local texture features when extracting global features of sample images and ignore the correlation between features in feature selection. Therefore, this paper proposes a new cashmere wool recognition method. First, Tamura features are combined with the gray-level co-occurrence matrix (GLCM) to extract texture features, which can add statistical characteristics of local regions. Second, a feature selection method based on LGB-RFECV is proposed, which use LightGBM’s leaf-wise growth strategy to choose the different feature subsets and then use RFECV to evaluate their performance and find the best feature subset. Finally, a LightGBM classification model optimized by Bayesian optimization is used to classify cashmere and wool. The simulation results show that the proposed method achieves a recognition accuracy of 98.61%, validating that the multifeature recognition method based on hybrid feature selection is effective for the identification of cashmere and wool.
XingWLiuYDengN, et al. Automatic identification of cashmere and wool fibers based on the morphological features analysis. Micron2020; 128: 102768.
2.
LuoJLuKZhongY, et al. Cashmere and wool identification based on convolutional neural network. J Eng Fibers Fabrics2021; 16: 15589250211005088.
3.
AnceschiAZoccolaMMossottiR, et al. Colorimetric quantification of virgin and recycled cashmere fibers: Equilibrium, kinetic, and thermodynamic studies. J Nat Fibers2022; 19(15): 11064-11077.
4.
ZhangXWuXYangH, et al. Identification of cashmere and wool by DNA barcode. J Nat Fibers2023; 20(1): 2175100.
5.
HaqueANMANaebeMMielewskiD, et al. Thermally stable micro-sized silica-modified wool powder from one-step alkaline treatment. Powder Technol2022; 404: 117517.
6.
ChenXLanQZhuY.Non-destructive identification of wool and cashmere fibers based on improved LDA using NIR spectroscopy. AUTEX Res J2024; 24(1): 20230017.
7.
AnceschiAZoccolaMMossottiR, et al. Colorimetric quantification of virgin and recycled cashmere fibers: Equilibrium, kinetic, and thermodynamic studies. J Nat Fibers2022; 19(15): 11064-11077.
8.
El NemrA.From natural to synthetic fibers. Textiles: Types, Uses and Production Methods, 2012: 1-152.
9.
WortmannFJArnsW.Quantitative fiber mixture analysis by scanning electron microscopy: Part I: blends of mohair and cashmere with sheep’s wool. Text Res J1986; 56(7): 442-446.
10.
HamlynPFNelsonGMcCarthyBJ.Wool-fibre Identification by means of novel species-specific DNA probes. J Text Inst1992; 83(1): 97–103.
11.
MarshallRCZahnHBlankenburgG.Possible identification of specialty fibers by electrophoresis. Text Res J1984; 54(2): 126-128.
12.
YuanSLLuKZhongYQ.Identification of wool and cashmere based on texture analysis. Key Eng Mater2015; 671: 385–390.
13.
LuKLuoJZhongY, et al. Identification of wool and cashmere SEM images based on SURF features. J Eng Fibers Fabrics2019; 14: 1558925019866121.
14.
XingWDengNXinB, et al. An image-based method for the automatic recognition of cashmere and wool fibers. Measurement2019; 141: 102-112.
15.
ZhuYHuangJWuT, et al. Identification method of cashmere and wool based on texture features of GLCM and Gabor. J Eng Fibers Fabrics2021; 16: 1558925021989179.
16.
ZhuYHuangJWuT, et al. An identification method of cashmere and wool by the two features fusion. Int J Cloth Sci Technol2022; 34(1): 13-20.
17.
ShigetoYSuzukiIHaraK, et al. Ridge regression, hubness, and zero-shot learning. In: Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Porto, 2015; pp. 135–151.
18.
ZhangLXiangTGongS.Learning a deep embedding model for zero-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2021–2030.
19.
ZhaoBWuBWuT, et al. Zero-shot learning posed as a missing data problem. In: IEEE International Conference on Computer Vision, 2017, pp. 2616–2622.
20.
ZhongYLuKTianJZhuH.Wool/cashmere identification based on projection curves. Text Res J2017; 87: 1730–1741. DOI: 10.1177/0040517516658516 .
21.
LuKChaiXXieH, et al. Identification of cashmere/wool based on pairwise rotation invariant co-occurrence local binary pattern. In: International Conference on Computational Science and Computational Intelligence (CSCI). IEEE, 2017, pp. 463-467.
22.
LuKZhongYQDuanL, et al. Cashmere/wool identification based on bag-of-words and spatial pyramid match. Text Res J2017; 88(21): 2435-2444.
23.
ZhuYZhaoLChenX, et al. Identification of cashmere and wool based on LBP and GLCM texture feature selection. J Eng Fibers Fabrics2023; 18: 1-12.
24.
MatsuoYLeCunYSahaniM, et al. Deep learning, reinforcement learning, and world models. Neur Netw2022; 152: 267-275.
25.
WangFJinX.The application of mixed-level model in convolutional neural networks for cashmere and wool identification. Int J Cloth Sci Technol2018; 30(5): 710-725.
26.
ZangLXinBDengN.Identification of wool and cashmere fibers based on multiscale geometric analysis. J Text Inst2022; 113(6): 1001-1008.
27.
ZhuYJiaYIHLiY, et al. Image identification of cashmere and wool fibers based on the improved Xception network. J King Saud Univ Comput Inf Sci2022; 34(10): 9301-9310.
28.
YaolinZRanLGangH, et al. Accurate identification of cashmere and wool fibers based on enhanced ShuffleNetV2 and transfer learning. J Big Data2023; 10(1): 152.
29.
GaoWZhangXYangL, et al. An improved Sobel edge detection. In: 2010 3rd International Conference on Computer Science and Information Technology. IEEE, 2010, vol. 5, pp. 67-71.
SaidKAMJambekAB.Analysis of image processing using morphological erosion and dilation. J Phys Conf Ser2021; 2071(1): 012033.
32.
AlturkiF AAbouel-KasemAAhmedSM.Characteristics of cavitation erosion using image processing techniques. Journal of Tribology, ASME, 2013; 135.
33.
PudjihartonoNFadasonTKempa-LiehrAW, et al. A review of feature selection methods for machine learning-based disease risk prediction. Front Bioinformat2022; 2: 927312.
34.
XingWLiuYDengN, et al. Automatic identification of cashmere and wool fibers based on the morphological features analysis. Micron2020; 128: 102768.
35.
SedgwickP.Independent samples t test. BMJ2010; 340(7758): c2673.
36.
SunC.Image classification of cashmere and wool fiber based on LC-KSVD. J Phys Conf Ser2021; 1948(1): 012010.
