Abstract
The research in the field of fabric characterization is reaching its zenith due to the increasing e-commerce activity and ever-growing digitalization of fabric information. With the increase in variety and heterogeneity of fabric classes, fabric characterization has become a very challenging task. Many approaches have been implemented to solve this problem, and the most common solutions are based on texture analysis. Since many fabrics, especially man-made fabrics have untextured or similar textured surfaces, it poses a problem to distinguish between them. Considering these complexities, an interesting way to solve this problem is to leverage the fabric’s reflection information. In this paper, the problem has been addressed using reflection property along with an SVM algorithm. Instead of deriving a complete reflectance model with an elaborate laboratory set-up, a model was developed where all that is needed is an image of the fabric taken using a regular commercial camera with an HDR feature, which captures the appearance in a single image under unknown natural illumination. This method was evaluated with a synthetic as well as a real-life data set, and it achieves an accuracy of 76.63% as compared to the human accuracy of 53.87%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ben Salem Y, Nasri S (2009) Texture classification of woven fabric based on a GLCM method and using multiclass support vector machine. In: 2009 6th international multi-conference on systems, signals and devices. Djerba, pp 1–8. https://doi.org/10.1109/ssd.2009.4956737
Zhang J, Marszalek M, Lazebnik S, Schmid C (2006) Local features and kernels for classification of texture and object categories: a comprehensive study. In: Proceedings of the 2006 conference on computer vision and pattern recognition workshop (CVPRW’06). IEEE Computer Society, Washington, DC, p 13. https://doi.org/10.1007/s11263-006-9794-4
Yang Y, Li J, Yang Y (2015) The research of the fast SVM classifier method. In: 2015 12th international computer conference on wavelet active media technology and information processing (ICCWAMTIP). IEEE, pp 121–124
Ghosh A, Guha T, Bhar RB, Das S (2011) Pattern classification of fabric defects using support vector machines. Int J Cloth Sci Technol 23(2/3):142–151. https://doi.org/10.1108/09556221111107333
Song A, Han Y, H H, Li Jianqing (2014) A novel texture sensor for fabric texture measurement and classification. Instrum Meas IEEE Trans On 63:1739–1747. https://doi.org/10.1109/TIM.2013.2293812
Zhang J, Palmer S, Wang X (2010) Identification of animal fibers with wavelet texture analysis. In: WCE 2010: proceedings of the world congress on engineering 2010. Newswood Limited/International Association of Engineers, Hong Kong, pp 742–747
Liu C, Gu J (2014) Discriminative illumination: per-pixel classification of raw materials based on optimal projections of spectral BRDF. IEEE Trans Pattern Anal Mach Intell 36:86–98. https://doi.org/10.1109/TPAMI.2013.110
Chandraker M, Ramamoorthi R (2011) What an image reveals about material reflectance. In: Proceedings of the 2011 international conference on computer vision (ICCV’11). IEEE Computer Society, Washington, DC, pp 1076–1083. https://doi.org/10.1109/iccv.2011.6126354
Nielsen JB, Jensen HW, Ramamoorthi R (2015) On optimal, minimal BRDF sampling for reflectance acquisition. ACM Trans Graph 34(6):11, Article 186 (October 2015). https://doi.org/10.1145/2816795.2818085
Georgoulis S, Vanweddingen V, Proesmans M, Gool LV (2017) Material classification under natural illumination using reflectance maps. In: 2017 IEEE winter conference on applications of computer vision (WACV), Santa Rosa, CA, pp 244–253. https://doi.org/10.1109/wacv.2017.34
Ahuja Y, Yadav SK (2012) Multiclass classification and support vector machine. Glob J Comput Sci Technol Interdiscip 12(11):14–20
Acknowledgements
This project was carried out under “Centre for Data Science and Applied Machine Learning”, PES University, India.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Katrak, K.K., Chandan, R., Lanka, S., Chitra, G.M., Shylaja, S.S. (2021). Sparse Reflectance Map-Based Fabric Characterization. In: Chiplunkar, N.N., Fukao, T. (eds) Advances in Artificial Intelligence and Data Engineering. AIDE 2019. Advances in Intelligent Systems and Computing, vol 1133. Springer, Singapore. https://doi.org/10.1007/978-981-15-3514-7_19
Download citation
DOI: https://doi.org/10.1007/978-981-15-3514-7_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3513-0
Online ISBN: 978-981-15-3514-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)