Textile Fiber Identification Using Near-Infrared Spectroscopy and Pattern Recognition

Abstract

Fibers are raw materials used for manufacturing yarns and fabrics, and their properties are closely related to the performances of their derivatives. It is indispensable to implement fiber identification in analyzing textile raw materials. In this paper, seven common fibers, including cotton, tencel, wool, cashmere, polyethylene terephthalate (PET), polylactic acid (PLA), and polypropylene (PP), were prepared. After analyzing the merits and demerits of the current methods used to identify fibers, near-infrared (NIR) spectroscopy was used owing to its significant superiorities, the foremost of which is it can capture the tiny information differences in chemical compositions and morphological features to display the characteristic spectral curve of each fiber. First, the fibers’ spectra were collected, and then, the relationships between the vibrations of characteristic chemical groups and the corresponding wavelengths were researched to organize a spectral information library that would be beneficial to achieve quick identification and classification. Finally, to achieve intelligent detection, pattern recognition approaches, including principal component analysis (PCA) (used to extract information of interest), soft independent modeling of class analogy (SIMCA), and linear discrimination analysis (LDA) (defined using two classifiers), assisted in accomplishing fiber identification. The experimental results – obtained by combining PCA and SIMCA – displayed that five of seven target fibers, namely, cotton, tencel, PP, PLA, and PET, were distributed with 100% recognition rate and 100% rejection rate, but wool and cashmere fibers yielded confusing results and led to relatively low recognition rate because of the high proportion of similarities between these two fibers. Therefore, the six spectral bands of interest unique to wool and cashmere fibers were selected, and the absorbance intensities were imported into the classifier LDA, where wool and cashmere were group-distributed in two different regions with 100% recognition rate. Consequently, the seven target fibers were accurately and quickly distinguished by the NIR method to guide the fiber identification of textile materials.

Reflectance FT-IR spectroscopy as a viable option for textile fiber identification

“…Unfortunately, most of the modern fibers (regenerated and synthetic) are almost identical in their morphology and thus cannot be identified reliably with microscopic visualization [2,6]. For fast analysis of textile fibers, often in (almost) non-destructive way, different vibrational spectroscopy approaches-Raman, near-infrared spectroscopy (NIR) and mid-infrared spectroscopy (IR)-have been used [1,4,5,[7][8][9][10][11]. Raman spectroscopy, while being widely used method in cultural heritage, [4,12,13] has a serious limitation when it comes to the identification of textile fibers.…”

Non-invasive identification of textile fibres using near-infrared fibre optics reflectance spectroscopy and multivariate classification techniques

“…Figure 2 shows the reflectance spectra of cotton, wool, and silk in the range 800-1700 nm (12,500-5882.35 cm −1 ). The absorption bands and their proposed assignments [22,26,30,31] are summarised in Table 4. Apart from some minor variation in reflectance intensity, the spectra are reproducible and dye and ageing does not influence significantly the spectra in the range studied.…”

“…Multivariate classification techniques may overcome this problem by building mathematical models, based on the spectral information, and identifying classes or groups by coding their similarities [28,29]. A consistent number of publications report on NIR spectroscopy and classification techniques for identifying textile fibres, both natural and synthetic, and their blends, particularly for industrial applications [15,[30][31][32][33]. For example, Howell and Davis [34] exploited Mahalanobis distances to classify four different synthetic fibres while Jasper and Kovacs [35] neural networks for classifying 17 fibre types.…”

“…They point out the difficulties to correctly differentiate between cotton and linen. Soft independent modelling of class analogy (SIMCA) was employed to classify nonblended fibres, both natural and synthetic [16], and compared with other methods-partial least squares discriminant analysis (PLS-DA) [31] and linear discriminant analysis (LDA) [30]. The fibre blends remain the main classification challenge.…”

Qualitative identification of waste textiles based on near-infrared spectroscopy and the back propagation artificial neural network

“…16 used the convolutional network classification method of normalized and pixelated NIRS to automatically classify nine types waste textiles, which effectively improved the detection level and speed of fabric components; Zhou et al. 17 used NIRS technology combined with principal component analysis (PCA) and the analogy soft independent modeling method to achieve the realization of cotton, Tencel, wool, cashmere, polyethylene terephthalate, polylactic acid (PLA) and polypropylene (PP) identification; Riba et al. 18 used on attenuated total reflection Fourier transform infrared (ATR-FTIR) technology combined with PCA, canonical variate analysis (CVA) and k -nearest neighbors (k-NN) mathematical methods to effectively identify and classify seven pure component fibers, providing a technical reference for the sorting of waste textiles.…”