|
|
|
| The Performance Evaluation of Classic ICA Algorithms for Blind Separation of Fabric Defects |
| College of Textile and Clothing Engineering, Soochow University, Suzhou 215000, China |
|
|
|
Abstract Independent Component Analysis (ICA) is a blind source separation technique that has been broadly
used in signal and image separation. In order to verify the feasibility of ICA algorithms which will
be used for the detection of fabric defect, four kinds of classic ICA algorithms have been chosen and
compared in terms of their algorithm performances. The results of simulation experiments show that the
separation performances of these algorithms are different and FastICA algorithm has the best separation
performance than others.
|
|
|
| Fund:
This work was financially supported by the Priority Academic Program Development of Jiangsu
Higher Education Institutions.
|
|
Corresponding Authors:
College of Textile and Clothing Engineering, Soochow University, Suzhou 215000, China
|
|
|
|
| Cite this article: |
|
Hailan Zhang,Zhonghao Cheng. The Performance Evaluation of Classic ICA Algorithms for Blind Separation of Fabric Defects[J]. Journal of Fiber Bioengineering and Informatics, 2014, 7(3): 377-386.
|
|
[1] HyvÄarinen A, Oja E. Independent component analysis: algorithms and applications. J Neural
Netw 2000; 13: 411-430.
[2] Kwak N, Choi CH. Feature extraction based on ICA for binary classification problems. IEEE Trans
Knowl Data Eng 2003; 15: 1374-1388.
[3] Talbar SN, Bodade RM. Feature Extraction of Iris Images using ICA for Person Authentication.
ICSPC 2007: 1055-1058.
[4] Draper BA, Baek K, Bartlett M S, et al. Recognizing faces with PCA and ICA. J Comput. Vis.
Image Understand 2003; 91: 115-137.
[5] Arakeri MP, Reddy GRM. A comparative performance evaluation of independent component anal-
ysis in medical image de-noising. ICRTIT 2011: 770-774.
[6] Gonzalez-Serrano FJ, Molina-Bulla HY, Murillo-Fuentes JJ. Independent component analysis ap-
plied to digital image watermarking. ICASSP 2001; 3: 1997-2000.
[7] Chiang SS, Chang CI, Ginsberg IW. Unsupervised hyper spectral image analysis using independent
component analysis. IGARSS 2000; 7: 3136-3138.
[8] Sezer OG, Ertiizun A, Er»cil A. Independent component analysis for texture defect detection. J
Pattern Recognit 2004; 14: 303-307.
[9] Tsai DM, Lin PC, Lu CJ. An independent component analysis-based filter design for defect de-
tection in low-contrast surface images. J Pattern Recognit 2006; 39: 1679-1694.
[10] Mahajan PM, Kolhe SR, Patil PM. A review of automatic fabric defect detection techniques. Adv
Comp Res 2009; 1: 18-29.
[11] Amari SI. Natural gradient works e±ciently in learning. J Neural Comput 1998; 10: 251-276.
[12] Bell AJ, Sejnowski TJ. An information-maximization approach to blind separation and blind
deconvolution. J Neural Comput 1995; 7: 1129-1159.
[13] Lee TW, Girolami M, Sejnowski TJ. Independent component analysis using an extended infomax
algorithm for mixed sub-gaussian and super-gaussian sources. J Neural Comput 1999; 11: 417-441.
[14] Hyvarinen A. Fast and robust fixed-point algorithms for independent component analysis. J Neural
Netw 1999; 10: 626-634.
[15] Mansour A, Kawamoto M, Ohnishi N. A survey of the performance indexes of ICA algorithms. J
MIC 2002: 660-666. |
|
|
|
2014, Vol. 7 
