Abstract
Seam pucker evaluation is based on the annotation of seam specimens into discrete grades of quality presenting an ordinal arrangement. Therefore, an ordinal logistic regression (OLR) model is highly qualified to fit the features extracted by such specimens into the assigned quality grades. This work focuses on building an automatic system for seam pucker evaluation based on an OLR model and comparing its performance with a similar system that employs an ordinary least squares (OLS) regression model. In this direction, three separate types of features have been extracted by a dataset of 325 seam images. The OLR model outperformed OLS for all feature types showing that its theoretical advantage applies also in practice. The best OLR model produced a correct classification rate of 81.2%, matching up to the performance of human experts.
Similar content being viewed by others
References
ISO 7770 (2009) Textiles—test method for assessing the smoothness appearance of seams in fabrics after cleansing
Fan J, Lu D, Macalpine JMK, Hui CLP (1999) Objective evaluation of pucker in three-dimensional garment seams. Textile Res J 69(7):467–472
Park CK, Kang TJ (1999) Objective evaluation of seam pucker using artificial intelligence. Part II: method of evaluating seam pucker. Textile Res J 69(11):835–845
Stylios G, Sotomi JO (1993) Investigation of seam pucker in lightweight synthetic fabrics as an aesthetic property. Part 1: a cognitive model for the measurement of seam pucker. J Textile Inst 84(4):593–600
Stylios G, Sotomi JO (1993) Investigation of seam pucker in lightweight synthetic fabrics as an aesthetic property. Part 2: model implementation using computer vision. J Textile Inst 84(4):601–610
Aibara T, Mabuchi T, Kenji O (1999) Automatic evaluation of the appearance of seam puckers on suits. Proc SPIE 3652:110–117
Bahlmann C, Heidemann G, Ritter H (1999) Artificial neural networks for automated quality control of textile seams. Pattern Recogn 32(6):1049–1060
Mariolis IG, Dermatas ES (2006) Automated quality control of textile seams based on puckering evaluation. In: 37th international symposium on novelties in textiles, Ljubljana, Slovenia
Koehl L, Miou JC, Zeng X (2007) Selecting relevant features from fabric images for automated quality control of seam puker using data analysis and human experts grading. In: Zeng X, Li Y, Ruan D, Koehl L (eds) Computational textile. Springer, Berlin, pp 39–54
Kang TJ, Kim SC, Sul IH, Youn JR, Chung K (2005) Fabric surface roughness evaluation using wavelet-fractal method. Part 1: wrinkle, smoothness, and seam pucker. Textile Res J 75(11):751–760
Zaouali R, Msahli S, El Abed B, Sakli F (2007) Objective evaluation of multidirectional fabric wrinkling using image analysis. J Textile Inst 98(5):443–451
Mariolis IG, Dermatas ES (2010) Automated assessment of textile seam quality based on surface roughness estimation. J Textile Inst 101(7):653–659
McCullagh P (1980) Regression models for ordinal data. J Royal Stat Soc Ser B (Methodology) 42(2):109–142
McCullagh P, Nelder J (1989) Generalized linear models. Chapman and Hall, London
Mariolis IG, Dermatas ES (2009) Illumination invariant seam line detection in real garments. Int J Cloth Sci Technol 21(5):286–299
Honda E, Domon M, Sasaki T (1991) A method for the determination of fractal dimensions of sialographic images. Investig Radiol 26(10):894–901
Kay SM (1993) Fundamentals of statistical signal processing, vol 1. Prentice-Hall, Upper Saddle River
Zhao L, Chen Y, Schaffner DW (2001) Comparison of logistic regression and linear regression in modeling percentage data. Appl Environ Microbiol 67(5):2129–2135
Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on artificial intelligence, vol 2. 12, pp 1137–1143
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mariolis, I.G., Dermatas, E.S. Automatic classification of seam pucker images based on ordinal quality grades. Pattern Anal Applic 16, 447–457 (2013). https://doi.org/10.1007/s10044-011-0241-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-011-0241-y