Traditional computer vision methods cannot match human performance well on fabric smoothness classification, as this is a subjective assessment based on sparse, comprehensive and low-cost visual perception. This paper reports a new assessment method of fabric smoothness appearance, including feature designing and wrinkle classification. A multidimensional feature was designed by generalizing vector quantization of dense scale-invariant feature transform (SIFT) descriptors for sparse coding and max pooling. Sparse coding provides clear understanding about the receptive fields of visual neurons and can build a codebook from the low features. A one-against-rest linear support vector machine (SVM) was utilized to classify the nine grades of smoothness and quantized to level 0.1 by space distance. Results showed that the proposed approach achieved remarkable classification accuracy in comparison with Bag-of-Feature (BOF) and Spatial Pyramid Matching (SPM) algorithms.
LiuCX. Investigation on the novel measurement for fabric wrinkle simulating actual wear. J Text I2016; 04: 1–10.
2.
LeonardoUSVictorL. Instrumentation system for objective evaluation of wrinkle appearance in fabrics using a standardized inspection booth. Text Res J2013; 84(4): 368–387.
3.
AATCC 124-2011. Smoothness appearance if fabrics agter repeated home laundering. AATCC Test Method: AATCC 2011.
4.
YingGJZhaoCCSuiJH. study on conventional method of test and evaluation of woven fabric's elasticity on wrinkle resistance. Adv Mater Res2013; 796: 221–224.
5.
ShinEHSeoMHJeonBSet al.Wrinkle components analysis using AATCC smoothness appearance replica. Text Sci & Eng2012; 49(1): 26–35.
6.
WangLLiuJLPanRRet al.Inspecting anisotropy in wrinkle recovery angle of woven fabric. J Text I2015; 107(6): 1–8.
7.
XuBGReedJA. Instrumental evaluation of fabric wrinkle recovery. J Text I1995; 86(1): 129–135.
8.
YangXBHuangXB. Evaluating fabric wrinkle degree with a photometric stereo method. Text Res J2003; 73(5): 451–454.
9.
YuWRXuBG. A sub-pixel stereo matching algorithm and its applications in fabric imaging. Mach Vision Appl2009; 20(4): 261–270.
10.
LiuCXZhangC. New method of fabric wrinkle measurement based on image processing. Fibers Text East Eur2014; 103(1): 51–55..
11.
XuBGYuWRWangRW. Stereovision for three-dimensional measurements of fabric pilling. Text Res J2011; 81(20): 2168–2179.
12.
XuPHDingXMWangRWet al.Feature-based 3D reconstruction of fabric by binocular stereo-vision. J Text I2016; 107(1): 12–22.
13.
YuWRYaoMXuBG. 3-D surface reconstruction and evaluation of wrinkled fabrics by stereo vision. Text Res J2009; 79(1): 36–46.
14.
LiuCXFuYQWuNY. Novel testing equipment for fabric wrinkle resistance simulating actual wear. Text Res J2014; 84(10): 1059–1069.
15.
Yao M. Fabric wrinkling and pilling evaluation by stereovision and three-dimensional surface characterization. PhD Thesis, The University of Texas at Austin, USA, 2012.
16.
Xin BJ. Characterization of fabric appearance based on image analysis. PhD Thesis, Hong Kong Polytechnic University, 2009.
17.
XinBJLiYMQiuJXet al.Texture modelling of fabric appearance evaluation based on image analysis. Fibers Text East Eur2012; 91(2): 48–52.
18.
JavierSBJoaquinBSRubénPLet al.Garment smoothness appearance evaluation through computer vision. Text Res J2012; 82(3): 299–309.
19.
HintonGESalakhutdinovRR. Reducing the dimensionality of data with neural networks. Science2006; 313(5786): 504–507.
20.
HintonGEOsinderoSTheYW. A fast learning algorithm for deep belief nets. Neural Comput2006; 18(7): 1527–1554.
21.
Thomas S, Lior W and Tomaso P. Object recognition with features inspired by visual cortex. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), San Diego, CA, USA, 20–26 June 2005, ISBN 0-7695-2372-2. Washington, DC, USA: IEEE Computer Society.
22.
CookeTFDusenburyJHKienleRHet al.Mechanism of imparting wrinkle recovery to cellulosic fabrics. Text Res J1954; 24(12): 1015–1036.
23.
ArmourR. How to tell a crease from a wrinkle. Sat Even Post1950; 223(14): 40–40.
24.
XuBGReedJA. Instrumental evaluation of fabric wrinkle recovery. J Text I1995; 86(1): 129–135.
25.
OrjuelaSABenhurOJEwoutVet al.Selection of optimal texture algorithms for evaluating degradation of carpets through experimental design. J Electron Imaging2013; 22(3): 1090–1098.
26.
TurnerCSari-SarrafHZhuAJet al.Automatic assessment of fabric smoothness. IEEE Circuits and Systems2002, 2: 379–382.
27.
LiuCXFuYQ. Novel measurement for multidirectional fabric wrinkling using wavelet analysis. Fiber Polym2014; 15(6): 1337–1342.
28.
SunJJYaoMXuBGPatricia Bel. Fabric wrinkle characterization and classification using modified wavelet coefficients and support-vector-machine classifiers. Text Res J2011; 81(9): 902–913.
29.
AbdolkarimHRRamazanAA. Objective evaluation of woven fabrics using optical sensors. Int J Sensors Wireless Comm & Contr2013; 2(3): 173–178.
30.
WangXHYaoM. Grading the crease recovery with twisting of fabric by using image identification technique. Int J Cloth Sci Tech2000; 12(2): 114–123.
31.
AmirbayatJAlaghaMJ. Objective assessment of wrinkle recovery by means of laser triangulation. J Text I1996; 87(2): 349–355.
32.
HuJLXinBJYanHJ. Measuring and modeling 3D wrinkles in fabrics. Text Res J2002; 72(10): 863–869.
33.
SuJXuBG. Fabric wrinkle evaluation using laser triangulation and neural network classifier. Opt Eng1999; 38(10): 1688–1693.
34.
ZhangZY. A flexible new technique for camera calibration. IEEE Trans Pattern Analy Mach Intell2000; 22(11): 1330–1334.
35.
Yang J, Jiang YG, Hauptmann AG, et al. Evaluating bag-of-visual-words representations in scene classification. In: Proceedings of the 9th ACM SIGMM International Workshop on Multimedia Information Retrieval, MIR 2007, Augsburg, Bavaria, Germany, 24–29 September 2007. New York, USA.
36.
Lazebnik S, Schmid C and Ponce J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), New York, NY, USA, 17–22 June 2006, ISBN 0-7695-2597-0. Washington, DC, USA: IEEE Computer Society.
37.
YangJCYuKGongYHet al.Linear spatial pyramid matching using sparse coding for image classification. IEEE CVPR2009, pp. 1794–1801.
38.
Yu K, Yang JC and Gong YH. Linear spatial pyramid matching using sparse coding. Patent US8374442 US 2013; 1794-1801.
39.
MikolajczykKSchmidC. A performance evaluation of local descriptors. IEEE Trans Pattern Anal Machine Intell2005; 27(10): 1615–1630.
40.
YaoBLiF. Grouplet: A structured image representation for recognizing human and object interactions. IEEE CVPR2010, pp. 9–16.
41.
CiresanDMeierUSchmidhuberJ. Multi-column deep neural networks for image classification. IEEE CVPR2012, pp. 3642–3649.
42.
LoweDG. Distinctive image features from scale-invariant keypoints. Int J Comput Vision2004; 60(2): 91–110.
43.
MutchJLoweDG. Multiclass object recognition with sparse,localized features. IEEE CVPR2006, pp. 11–18.
44.
AvilaSThomeNMatthieuCet al.Pooling in image representation: The visual codeword point of view. Comput Vis Image Und2013; 117(5): 453–465.
45.
CsurkaGDanceCRFanLet al.Visual categorization with bags of keypoints. ECCV2004, pp. 22–26.
