Determination and Comparison of Fabric Pills Distribution Using Image Processing and Spatial Data Analysis Tools

Authors: Lenka Techniková, Maroš Tunák, Jiří Janáček

Abstract:

This work deals with the determination and comparison of pill patterns in 2 sets of fabric samples which differ in way of pill creation. The first set contains fabric samples with the pills created by simulation on a Martindale abrasion machine, while pills in the second set originated during normal wearing and maintenance. The goal of the study is to determine whether the pattern of the fabric pills created by simulation is the same as the pattern of naturally occurring pills. The system of determination and comparison of the pills is based on image processing and spatial data analysis tools. Firstly, 3D reconstruction of the fabric surfaces with the pills is realized with using a gradient fields method. The gradient fields method creates a 3D fabric surface from a set of 4 images. Thereafter, the pills are detected in 3D fabric surfaces using image-processing tools in the MATLAB software. Determination and comparison of the pills patterns of two sets of fabric samples is based on spatial data analysis using tools in R software.

Keywords: 3D reconstruction of the surface, image analysis tools, distribution of the pills, spatial data analysis tools.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1088146

References:

[1] Ucar, N., Boyraz, P.: Measurement of Fuzz Fibers on Fabric Surface
[2] Semnani, D., Ghayoor, H.: Detecting and Measuring Fabric Pills Using Digital Image Analysis. World Academy of Science, Engineering and Technology, 49, 897 (2009).
[3] Xu, B: Instrumental Evaluation of Fabric Pilling. Journal of Tex. Institute, 88, 488 (1997).
[4] Xiaojun, L., Huabing, H., Yushu, L., Hong, Z.: The Evaluation System of Fabric Pilling Based on Image Processing Technique. IEEE Image Analysis and Signal Processing, 1, 44 (2009).
[5] Kim, S., Kang, T.: Image Analysis of Standard Pilling Photographs Using Wavelet Reconstruction. Textile Res. J., 75(12), 801 (2005).
[6] Zhang, J., Wang, X., Palmer, S.: Performance of an Objective Fabric Pilling Evaluation Method. Textile Res. J., 80(16), 1648 (2010).
[7] Palmer, S., Zhang, J., Wang, X.: New Methods for Objective Evaluation of Fabric Pilling by Frequency Domain Image Processing. Research Journal of Textile and Apparel, 13(1), 11 (2009).
[8] Xu, B., Yu, W.,Wang, R.: Stereovision for Three – Dimensional Measurements of Fabric Pilling. Textile Res. J., 81(20), 2168 (2011).
[9] Agrawal, A., Chellappa, R.: An Algebraic Approach to Surface Reconstruction from Gradient Fields. 8th European Conference on Computer Vision, vol. 1, pp. 174 – 181 (2005).
[10] Agrawal, A., Raskar, R., Chellappa, R..: What is the Range of Surface Reconstructions from a Gradient Field? 9th European Conference on Computer Vision, vol. 2, pp. 578-591 (2006).
[11] Techniková, L., Tunák, M. and Janáček, J: Forming of 3D Fabric Surface with the Help of Gradient Fields and Detection of the Pills. Adv. Sci. Lett., vol. 19, pp. 203-206 (2013).
[12] Gonzales, R.C., Wood, R.E.: Digital Image Processing. 2nd edition, Prentice-Hall, 2002.
[13] A. Baddeley and R. Turner. Spatstat: an R package for analyzing spatial point patterns. Journal of Statistical Software, 12(6):1–42, 2005. URL: www.jstatsoft.org, ISSN: 1548-7660.
[14] Diggle, P.: Statistical Analysis of Spatial Point Patterns. Academic Press, 1983.
[15] Philimonenko, A., Janáček, J., Hozák, P.: Statistical Evaluation of Colocalization Patterns in Immunogold Labeling Experiments. Journal of Structural Biology 132, 201–210 (2000).