The convolutional neural network (CNN) has recently achieved great breakthroughs in many computer vision tasks. However, its application in fabric texture defects classification has not been thoroughly researched. To this end, this paper carries out a research on its application based on the CNN model. Meanwhile, since the CNN cannot achieve good classification accuracy in small sample sizes, a new method combining compressive sensing and the convolutional neural network (CS-CNN) is proposed. Specifically, this paper uses the compressive sampling theorem to compress and augment the data in small sample sizes; then the CNN can be employed to classify the data features directly from compressive sampling; finally, we use the test data to verify the classification performance of the method. The explanatory experimental results demonstrate that, in comparison with the state-of-the-art methods for running time, our CS-CNN approach can effectively improve the classification accuracy in fabric defect samples, even with a small number of defect samples.
ZhengDJHanYJinL. A new method for classification of woven structure for yarns-dyed fabric. Text Res J2014; 84: 78–95.
2.
MehtaREgiazarianK. Texture classification using dense micro-block difference. IEEE Trans Image Proc2016; 25: 1604–1616.
3.
BoulkenafetZKomulainenJHadidA. Face spoofing detection using colour texture analysis. IEEE Trans Inform Forens Secur2016; 11: 1818–1830.
4.
AlliliMSBaazizNMejriM. Texture modeling using contourlets and finite mixtures of generalized Gaussian distributions and applications. IEEE Trans Multimedia2014; 16: 772–784.
5.
ShadyEGowayedYAbouiianaM. Detection and classification of defects in knitted fabric structures. Text Res J2006; 76: 295–300.
6.
ConnorJBryanBANolanM. Modeling Australian land use competition and ecosystem services with food price feedbacks at high spatial resolution. Environ Model Software2015; 69: 141–154.
7.
XinBJZhangJZhangR. Color texture classification of yarn-dyed woven fabric based on dual-side scanning and co-occurrence matrix. Text Res J2017; 87: 1883–1895.
8.
TabassianMGhaderiREbrahimpourR. Knitted fabric defect classification for uncertain labels based on Dempster-Shafer theory of evidence. Expert Syst Appl2011; 38: 5259–5267.
9.
Zhang Y, Lu Z and Li J. Fabric defect detection and classification using Gabor filters and Gaussian mixture model. In: Hongbin Z, Rin-ichiro T and Stephen M (eds) 9th Asian conference on computer vision, Xi’an, China, 23–27 September 2009, pp.635–644. Berlin, Heidelberg: Springer.
10.
TongLWongWKKwongCK. Differential evolution-based optimal Gabor filter model for fabric inspection. Neurocomputing2016; 173: 1386–1401.
11.
XuPHDingXMWuXY. Characterization and assessment of fabric smoothness appearance based on sparse coding. Text Res J2018; 88: 367–378.
12.
LiWChengL. Yarn-dyed woven defect characterization and classification using combined features and support vector machine. J Text Inst2014; 105: 163–174.
13.
YildizKDemetgulAB. A thermal-based defect classification method in textile fabrics with K-nearest neighbor algorithm. J Ind Text2016; 45: 780–795.
14.
KuoCFJuangY. A study on the recognition and classification of embroidered textile defects in manufacturing. Text Res J2016; 86: 207–212.
15.
ChenLFLiaoHYMKoMT. A new LDA-based face recognition system which can solve the small sample size problem. Pattern Recognit2000; 33: 1713–1726.
16.
MaryamIHassanG. Band clustering-based feature extraction for classification of hyperspectral images using limited training samples. IEEE Geosci Remote Sens Lett2014; 11: 1325–1329.
17.
MaryamIHassanG. Feature extraction using attraction points for classification of hyperspectral images in a small sample size situation. IEEE Geosci Remote Sens Lett2014; 11: 1986–1990.
18.
ZhangZFSongYCuiHC, et al.Topological analysis and Gaussian decision tree: Effective representation and classification of biosignals of small sample size. IEEE Trans Biomed Eng2017; 64: 2288–2299.
19.
ShuXYuHMZhengWW. Classifier-designing algorithm on a small dataset based on margin fisher criterion and transfer learning. Acta Automatica Sinica2016; 42: 1313–1321.
20.
LiJYZhangHYZhangLP. A nonlinear multiple feature learning classifier for hyperspectral images with limited training samples. IEEE J Select Topic Appl Earth Observ Remote Sens2015; 8: 2728–2738.
21.
HamidullahBGokhanBSemihD. Kernel Fukunaga-Koontz transform subspaces for classification of hyperspectral images with small sizes. IEEE Geosci Remote Sens Lett2015; 12: 1287–1291.
22.
AydemirMSBilginG. Semisupervised hyperspectral image classification using small sample sizes. IEEE Geosci Remote Sens Lett2017; 14: 621–625.
23.
DonohoDL. Compressed sensing. IEEE Trans Inform Theor2006; 52: 1289–1306.
24.
ChenCLZLiSQinH, et al.Real-time and robust object tracking in video via low-rank coherency analysis in feature space. Pattern Recognit2015; 48: 2885–2905.
25.
JiaMGaoZGuoQ. Fast compressive tracking with robust example selection based on multiple instance learning in smart and autonomous systems. Pattern Recognit2017; 69: 336–351.
26.
LorenzoPGiacomoOFedericoV, et al.MT-BCS-based microwave imaging approach through minimum-norm current expansion. IEEE Trans Antenna Propagat2013; 61: 4722–4732.
27.
GiulioCSimeonKKAndreaA, et al.Progressive compressed sensing and reconstruction of multidimensional signals using hybrid transform/prediction sparsity model. IEEE J Emerg Select Topic Circ Syst2012; 2: 340–352.
28.
MehtaJMajumdarA. RODEO: Robust DE-aliasing autoencoder for real time medical image reconstruction. Pattern Recognit2017; 63: 499–510.
29.
NiranjanMGArunPK. Interferer identification in HerNets using compressive sensing framework. IEEE Trans Commun2013; 61: 4780–4787.
30.
WangZLiHSZhangQW. Magnetic resonance fingerprinting with compressed sensing and distance metric learning. Neurocomputing2016; 174: 560–570.
31.
LiLStolkinRJiaoL, et al.A compressed sensing approach for efficient ensemble learning. Pattern Recognit2014; 47: 3451–3465.
32.
LiYXieWLiH. Hyperspectral image reconstruction by deep convolutional neural network for classification. Pattern Recognit2017; 63: 371–383.
33.
WeiYCXiaWLinM, et al.HCP: A flexible CNN framework for multi-label image classification. IEEE Trans Pattern Anal Mach Intell2016; 38: 1091–1097.
34.
Yu YC, Hao KR and Ding YS. A new image classification model based on brain parallel interaction mechanism. Neurocomputing. 2018; 315: 190–197.
35.
XieGSZhangXYYanSC, et al.Hybrid CNN and dictionary-based models for scene recognition and domain adaption. IEEE Trans Circ Syst Video Technol2017; 27: 1263–1274.
36.
XieFYShiMYShiZW, et al.Multilevel cloud detection in remote sensing images based on deep learning. IEEE J Select Topic Appl Earth Observ Remote Sens2017; 10: 3631–3640.
37.
CaoJJZhangJWenZJ. Fabric defect inspection using prior knowledge guided least squares regression. Multimedia Tool Appl2017; 76: 4141–4157.
38.
JingJFDongALiPF. Yarn-dyed fabric defect classification based on convolutional neural network. Opt Eng2017; 56: 1–9.
39.
Wang XX, Chen Z, Liu GH, et al. Fiber image classification using convolutional neural networks. In: 4th international conference on systems and informatics, Hangzhou, China, 11–13 November 2017, pp.11–13. IEEE.
40.
LiYDZhangJLinY. Combining fisher criterion and deep learning for patterned fabric defect inspection. IEICE Trans Informat Syst2016; E99D: 2840–2842.
41.
LiYZhaoWPanJ. Deformable patterned fabric defect detection with fisher criterion-based deep learning. IEEE Trans Automat Sci Eng2017; 14: 1256–1264.
42.
MeiSWangYDWenGJ. Automatic fabric defect detection with a multi-scale convolutional denoising autoencoder network model. Sensors2018; 18: 1–18.
43.
RichardGBEmmanuelCRobertN. Compressive sampling. IEEE Signal Proc Mag2008; 25: 12–13.
44.
CandesEJ. Compressive sampling. Marta Sanz Sole2007; 17: 1433–1452.
45.
ChengGYangCYYaoXW, et al.When deep learning meets metric learning: remote sensing image scene classification via learning discriminative CNNs. IEEE Trans Geosci Remote Sensing2018; 56: 2811–2821.
46.
RauhutHSchnassKVandergheynstP. Compressed sensing and redundant dictionaries. IEEE Trans Inform Theor2008; 54: 2210–2219.
47.
Wu K and Guo X. Compressive sensing with sparse measurement matrices. In: proceedings of the 73rd IEEE vehicular technology conference, Yokohama, Japan, 15–18 May 2011, pp.1–5. IEEE.
48.
TsaigYDonohoDL. Extensions of compressed sensing. Signal Proc2006; 86: 549–571.
49.
YuNYZhaoN. Deterministic of real-valued ternary sensing matrices using optical orthogonal codes. IEEE Signal Proc Lett2013; 20: 1106–1109.
