A novel method combining the characteristics of corner information and second-order statistics of fabric images is proposed for analyzing the repeat size and identifying the weave type of fabrics. The analysis method is formulated in a research framework of near regular texture analysis. Firstly, the original fabric image is split into two components: the geometric component and the textural component, in which low-level cues of corners are detected by the Harris detector. Secondly, clustering techniques are used to cluster interest points by image patch appearance. Thirdly, a Markov Random Field (MRF) model is adopted for inferring the location of texture elements, and their shape is then used for classifying the weave patterns. The experimental results show that the main disadvantages and difficulties of using structural and frequency methods in texture classifications have been overcome by the proposed method.
KuoCTsaiC. Automatic recognition of fabric nature by using the approach of texture analysis. Text Res J2006; 76: 375–381.
2.
HuangCLiuSYuW. Woven fabric analysis by image processing, Part I: Identification of weave patterns. Text Res J2000; 70: 481–485.
3.
YuXXinBBaciuGHuJ. Fourier-analysis based satin fabric density and weaving pattern extraction. Res J Text Apparel2007; 11: 71–80.
4.
PanRGaoWLiuJ. Automatic detection of structure parameters of yarn-dyed fabric. Text Res J2010; 80: 1819–1832.
5.
KangTKimC. Automatic recognition of fabric weave patterns by digital image analysis. Text Res J1999; 69: 77–83.
6.
JeonBBaeJSuhM. Automatic recognition of woven fabric patterns by an artificial neural network. Text Res J2003; 73: 645–650.
7.
AjallouianaFTavanaiaHPalhangbM. A novel method for the identification of weave repeat through image processing. J Text Inst2009; 100: 195–206.
8.
KuoCShihCLeeJ. Automatic recognition of fabric weave patterns by a fuzzy c-means clustering method. Text Res J2004; 74: 107–111.
9.
LachkarABenslimaneRD'OrazioL. Textile woven fabric recognition using Fourier image analysis techniques: Part II-texture analysis for crossed-states detection. J Text Inst2005; 96: 179–183.
10.
RavandiSToriumiK. Fourier transform analysis of plain weave fabric appearance. Text Res J1995; 65: 676–683.
11.
LiuYLinWHaysJ. Near-regular texture analysis and manipulation. ACM T Graphic2004; 23: 366–374.
12.
SuTKuoYChenH. Grey relational analysis of an automatic identifying system for clothing texture. Fibers Text East Eur2010; 18: 60–64.
13.
CaiYBaciuG. Higher level segmentation: Detecting and grouping of invariant repetitive patterns. Proc CPVR IEEE2012, pp. 694–701.
14.
ChambolleALionsP. Image recovery via total variation minimization and related problems. Numer Math1997; 76: 167–188.
15.
VeseLOsherS. Modeling textures with total variation minimization and oscillating patterns in image processing. J Sci Comput2003; 19: 553–572.
16.
VeseL. A study in the BV space of a denoising-deblurring variational problem. Appl Math Opt2001; 44: 131–161.
17.
AujolJGilboaGChanT. Structure–texture image decomposition—modeling, algorithms, and parameter selection. Int J Comput Vision2006; 67: 111–136.
18.
HarrisCStephensM. A combined corner and edge detector. Fourth Alvery Vision Conference, Manchester, UK, 1988, pp. 147–151.
19.
TissainayagamPSuterD. Assessing the performance of corner detectors for point feature tracking applications. Image Vision Comput2004; 22: 663–679.
20.
ComaniciuDMeerP. Mean shift: A robust approach toward feature space analysis. IEEE T Patt Anal2002; 24: 603–619.
21.
ParkMLiuYCollinsR. Efficient mean shift belief propagation for vision tracking. Proc IEEE Conf Comput Vision Patt Recog2008, pp. 1–8.
22.
ParkMBrocklehurstKCollinsRT. Deformed lattice detection in real-world images using mean-shift belief propagation. IEEE T Patt Anal2009; 31: 1804–1816.
23.
ZhengDBaciuGHuJ. Entropy-based fabric weave pattern indexing and classification. International Journal of Cognitive Informatics and Natural Intelligence2010; 4: 76–92.
24.
SchindlerGKrishnamurthyPLublinermanR. Detecting and matching repeated patterns for automatic geo-tagging in urban environments. Proc IEEE Conf Comput Vision Patt Recog2008, pp. 1–8.
25.
KuoCJianBTungC. Automatic machine embroidery image color analysis system, part II: Application of the genetic algorithm in search of a repetitive pattern image. Text Res J2012; 82: 1099–1106.
26.
PanRGaoWLiuJ. Automatic detection of the layout of color yarns for yarn-dyed fabric via a FCM algorithm. Text Res J2010; 80: 1222–1231.
27.
MoussaADupontDSteenD. Structure analysis and surface simulation of woven fabrics using fast Fourier transform techniques. J Textile Inst2010; 101: 556–570.
