A Method for the Assessment of Textile Pilling Tendency Using Optical Coherence Tomography

Abstract

<jats:p>Pilling is caused by friction pulling and fuzzing the fibers of a material. Pilling is normally evaluated by visually counting the pills on a flat fabric surface. Here, we propose an objective method of pilling assessment, based on the textural characteristics of the fabric shown in optical coherence tomography (OCT) images. The pilling layer is first identified above the fabric surface. The percentage of protruding fiber pixels and Haralick’s textural features are then used as pilling descriptors. Principal component analysis (PCA) is employed to select strongly correlated features and then reduce the feature space dimensionality. The first principal component is used to quantify the intensity of fabric pilling. The results of experimental studies confirm that this method can determine the intensity of pilling. Unlike traditional methods of pilling assessment, it can also detect pilling in its early stages. The approach could help to prevent overestimation of the degree of pilling, thereby avoiding unnecessary procedures, such as mechanical removal of entangled fibers. However, the research covered a narrow group of fabrics and wider conclusions about the usefulness and limitations of this method can be drawn after examining fabrics of different thickness and chemical composition of fibers.</jats:p>

Changes in Fabric Surface Pilling under Laser Ablation

“…To choose the proper parameters of the laser beam, several tests were performed. The range of the parameters of the laser were chosen based on previous studies [ 19 ]. The focusing lens and F-Theta objective allows a single mode of laser beam radiation to be obtained, in the shape of a gaussian mode.…”

“…This stage is responsible for extraction of the pilling layer L P located above the fabric surface and regarded as a separated image J ( x,y,z ). We have described the detection principle of this layer in a previous article [ 19 ].…”

“…In our opinion, the commonly used method of visual assessment is too subjective [ 18 ]. Therefore, we use a newly developed method for computer assessment of pilling, using optical coherent tomography (OCT), which we presented in a previous publication [ 19 ]. Optical coherence tomography is a noninvasive imaging technology based on low-coherence interferometry [ 20 , 21 , 22 ].…”

“…Optical coherence tomography can also be applied as a tool for testing surface roughness [ 31 ], composite material layers [ 32 ], food products [ 33 ], printed circuit boards [ 34 ], and solar cells [ 35 ], as well as in polymer science [ 36 ]. In textile sciences, OCT has been used to sort fabrics [ 37 ], assess industrial laundry cleaning [ 38 ], and evaluate the degree of fabric pilling [ 19 ]. Currently, advanced TD-OCT and FD-OCT optical systems are quite expensive, which limits their usage.…”

Comparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography

“…The problem with using invasive sensors is the inability to directly examine any part of the reactor's interior, the accuracy of the measurements taken, the requirement to use multiple monitoring systems at the same time, and the high uncertainty in determining the dynamic state of the process based on incomplete data (indirect method). Electrical capacitance tomography (ECT) [4][5][6][7][8][9][10][11][12][13][14][15][16], electrical impedance tomography (EIT) [17][18][19][20][21][22][23][24], magnetoacoustic tomography [25], ultrasound and radio [26,27], X-ray tomography [28], optical tomography [29,30], and other non-invasive technologies are used to monitor industrial operations. Recently, an increasing number of research papers in the field of industrial system operation have included the use of various computational methods, such as intelligent predictive methods [31], fuzzy logic [32,33], machine learning [34], numerical modelling [35], deep learning [18,36], and binary programming [37].…”