Fabric defect detection via small scale over-complete basis set

被引:37
作者
Zhu, Qiuping [1 ]
Wu, Minyuan [1 ]
Li, Jie [1 ]
Deng, Dexiang [1 ]
机构
[1] Wuhan Univ, Sch Elect Informat, Wuhan 430079, Hubei, Peoples R China
关键词
defect detection; over-complete basis set; sparse coding; Gabor filter; TEXTURE; FOURIER; REGULARITY; MODEL;
D O I
10.1177/0040517514525880
中图分类号
TB3 [工程材料学]; TS1 [纺织工业、染整工业];
学科分类号
0805 ; 080502 ; 0821 ;
摘要
Defect detection has been a focal point in fabric inspection research and remains challenging. In this paper, a novel method for fabric defect detection is presented. In the proposed algorithm, only defect-free fabric images are used to build the over-complete basis set via sparse coding. Compared to traditional defect detection methods via sparse coding, our method uses a Gabor filter to reduce the complexity of the fabric signal, and takes the fabric patch's projections in the small scale over-complete basis set as the original features, not the sparse representation. We compare the averages of the patch and its neighborhoods' features with the standard features, which are the averages of all defect-free fabric images' features. At last, according to this compared distance, the patch is classified as defective or non-defective. The experimental results on our own database and the TILDA database reveal that our features are more robust and the proposed algorithm can detect defects on twill, plain, gingham and striped fabric effectively.
引用
收藏
页码:1634 / 1649
页数:16
相关论文
共 31 条
[1]  
Asha V, 2011, COMM COM INF SC, V157, P548
[2]  
Basturk A., 2007, 2007 9th International Symposium on Signal Processing and Its Applications, P1
[3]   The ''independent components'' of natural scenes are edge filters [J].
Bell, AJ ;
Sejnowski, TJ .
VISION RESEARCH, 1997, 37 (23) :3327-3338
[4]   Fabric defect detection using undecimated wavelet transform [J].
Bi M. ;
Sun Z. .
Information Technology Journal, 2011, 10 (09) :1701-1708
[5]   Fabric defect detection based on multiple fractal features and support vector data description [J].
Bu, Hong-gang ;
Wang, Jun ;
Huang, Xiu-bao .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2009, 22 (02) :224-235
[6]   Finding defects in texture using regularity and local orientation [J].
Chetverikov, D ;
Hanbury, A .
PATTERN RECOGNITION, 2002, 35 (10) :2165-2180
[7]  
Chi-Ho Chan, 1999, Conference Record of the 1999 IEEE Industry Applications Conference. Thirty-Forth IAS Annual Meeting (Cat. No.99CH36370), P1743, DOI 10.1109/IAS.1999.805975
[8]   Textural defect segmentation using a Fourier-Domain maximum likelihood estimation method [J].
Chiu, SH ;
Chou, S ;
Liaw, JJ .
TEXTILE RESEARCH JOURNAL, 2002, 72 (03) :253-258
[9]   Fabric Defect Detection Scheme Based on Gabor filter and PCA [J].
Ding, Shumin ;
Li, Chunlei ;
Liu, Zhoufeng .
ADVANCED COMPOSITE MATERIALS, PTS 1-3, 2012, 482-484 :159-163
[10]  
Heidari N., 2011, INT J IMAGE PROCESS, V5, P25, DOI DOI 10.1049/IET-IPR.2009.0340