Intelligent Identification of Chinese and Australian Merino Wool Fibers Based on Image Recognition

Abstract:

In order to promote the sustainable growth of the wool industry and protect consumers' legitimate rights, rapid identification of the country of origin for wool of the same type is deemed crucial. This research presents a computer graphic recognition training model that utilizes median and Wiener filtering techniques to effectively reduce noise in the raw wool fiber images. Employing a support vector machine as the classifier and integrating a polynomial kernel function, this model achieves swift and accurate identification of Chinese and Australian Merino wool fibers. Experimental results underscore that following image recognition training, the model attains an impressive 92.5% comprehensive and precise identification rate for Chinese and Australian Merino wool fibers, effectively distinguishing the origin of wool from the same category. This approach not only provides a valuable reference for identifying the origin of similar wool types but also holds the potential to standardizing the wool fibre material market and assuring the consumer’s confidence on wool products.

• Periodical: Key Engineering Materials (Volume 978)
• Pages: 143-148
• DOI: https://doi.org/10.4028/p-O96baR
• Online since: March 2024
• Authors: Xiao Bo Wang, Zhan Xia Chen, Li Jing Wang, Xue Lei Shan, Zi Li Xie, Yun Long Shi, Xiao Ming Qian*
• Keywords: Fiber Classification, Image Processing, Intelligent Recognition, Support Vector Machine, Wool Fiber Origin

References

[1] Wiedemann S G, Yan M J, Henry B K, et al. Resource use and greenhouse gas emissions from three wool production regions in Australia. Journal of Cleaner Production, 2016, 122: 121-132

DOI: 10.1016/j.jclepro.2016.02.025

[2] Fanwen L, Yazhou W. Application Effect of Key Technology for Fine Wool Production. Animal Husbandry and Feed Science, 2018, 10(4): 216-218

DOI: 10.3390/buildings11080352

[3] Gibson P, Ville S. Australian Wool and Chinese Industrialization, 1901–1941. Twentieth-Century China, 2019, 44(3): 265-287

DOI: 10.1353/tcc.2019.0030

[4] Mujumdar N, Heider E C, Campiglia A D. Enhancing textile fiber identification with detergent fluorescence. Applied spectroscopy, 2015, 69(12): 1390-1396

DOI: 10.1366/15-07992

[5] Gill R, Gill S, Slyadnev M, et al. Identification and quantitation of cashmere (pashmina) fiber and wool using novel microchip based real-time PCR technology. Journal of Textile Science and Technology, 2018, 4(04): 141

DOI: 10.4236/jtst.2018.44010

[6] Huang M, Zhu J, Wu J. A fast classification method based on sequential Bayesian analysis for figures in irradiation images. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2019, 946: 162699

DOI: 10.1016/j.nima.2019.162699

[7] Xing W, Deng N, Xin B, et al. An image-based method for the automatic recognition of cashmere and wool fibers. Measurement, 2019, 141: 102-112. DOI: 10.1016/j.measurement. 2019.04.015

DOI: 10.1016/j.measurement.2019.04.015

[8] Yuan S L, Lu K, Zhong Y Q. Identification of wool and cashmere based on texture analysis. Key Engineering Materials, 2016, 671: 385-390. DOI:10.4028/www.scientific.net/ KEM.671.385

DOI: 10.4028/www.scientific.net/kem.671.385

[9] Maya V K, S. Sethu S. Multi-Algorithm Fusion for Fingerprint Recognition Based on Texture Features. Biometrics and Bioinformatics, 2012, 4(4).

[10] Afradi A, Ebrahimabadi A. Comparison of artificial neural networks (ANN), support vector machine (SVM) and gene expression programming (GEP) approaches for predicting TBM penetration rate. SN Applied Sciences, 2020, 2: 1-16

DOI: 10.1007/s42452-020-03767-y

[11] Bhavsar H, Panchal M H. A review on support vector machine for data classification. International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), 2012, 1(10): 185-189.